diff --git a/create-xpr-agent/package.json b/create-xpr-agent/package.json
index 63d7174..503fe16 100644
--- a/create-xpr-agent/package.json
+++ b/create-xpr-agent/package.json
@@ -1,6 +1,6 @@
 {
   "name": "create-xpr-agent",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "description": "Create an autonomous AI agent on XPR Network",
   "type": "module",
   "bin": "./create.mjs",
diff --git a/create-xpr-agent/template/.env.example b/create-xpr-agent/template/.env.example
index 479926d..87d555e 100644
--- a/create-xpr-agent/template/.env.example
+++ b/create-xpr-agent/template/.env.example
@@ -112,8 +112,10 @@ AGENT_SKILLS=
 # Enable built-in poller (checks chain state, no indexer needed)
 POLL_ENABLED=true
 
-# Poll interval in seconds (default: 30)
-POLL_INTERVAL=30
+# Poll interval in seconds (default: 60)
+# Tune lower for snappier job pickup, higher to be gentler on shared RPC.
+# The agent runner accepts values as low as 5s.
+POLL_INTERVAL=60
 
 # ── Telegram Bridge ──────────────────────────
 # Bot token from @BotFather. Leave empty to disable.
diff --git a/create-xpr-agent/template/README.md b/create-xpr-agent/template/README.md
index f47568e..d65fc4b 100644
--- a/create-xpr-agent/template/README.md
+++ b/create-xpr-agent/template/README.md
@@ -169,12 +169,14 @@ All configuration is stored in `.env` (auto-generated by `start.sh`). **There is
 
 | Variable | Required | Default | Description |
 |----------|----------|---------|-------------|
-| `XPR_ACCOUNT` | Yes | — | Agent account name (proton CLI must have its key loaded) |
+| `XPR_ACCOUNT` | Yes | — | Agent account name (proton CLI must have its key loaded). Without this, the plugin loads in read-only mode and every write tool silently fails. |
 | `ANTHROPIC_API_KEY` | Yes | — | Anthropic API key |
+| `XPR_NETWORK` | No | `mainnet` | Network (`mainnet` or `testnet`) |
+| `XPR_RPC_ENDPOINT` | No | auto from network | Chain RPC endpoint — leave unset to auto-select |
+| `INDEXER_URL` | No | `https://indexer.xpragents.com` | Public XPR Agents indexer. 4 read tools depend on this. Override only if you run your own. |
+| `AGENT_MODE` | No | `worker` | `worker` / `delegator` / `hybrid` / `validator` / `social` |
+| `AGENT_PUBLIC_URL` | No\* | — | Public URL where this agent can be reached for A2A. **\*Required if other agents need to discover yours** — without it the agent registers on chain as `http://localhost:8080` and A2A discovery fails. |
 | `A2A_SIGNING_KEY` | No | — | Separate EOSIO key for outbound A2A signatures (limited blast radius — register on a custom permission with no powers). If unset, A2A runs receive-only. |
-| `XPR_NETWORK` | No | `testnet` | Network (testnet/mainnet) |
-| `XPR_RPC_ENDPOINT` | No | testnet RPC | Chain RPC endpoint |
-| `HYPERION_ENDPOINTS` | No | testnet Hyperion | Hyperion stream endpoint |
 | `AGENT_MODEL` | No | `claude-sonnet-4-6` | Claude model for decisions |
 | `AGENT_MAX_TURNS` | No | `20` | Max tool-call turns per event |
 | `MAX_TRANSFER_AMOUNT` | No | `10000000` | Max XPR per transfer (smallest units, 10000000 = 1000 XPR) |
@@ -186,7 +188,7 @@ All configuration is stored in `.env` (auto-generated by `start.sh`). **There is
 | `A2A_TOOL_MODE` | No | `full` | Tool access for A2A callers: `full` or `readonly` |
 | `COST_MARGIN` | No | `2.0` | Profit margin multiplier for cost estimates (2.0 = 100% markup) |
 | `POLL_ENABLED` | No | `true` | Enable built-in on-chain poller |
-| `POLL_INTERVAL` | No | `30` | Poll interval in seconds |
+| `POLL_INTERVAL` | No | `60` | Poll interval in seconds (lower = snappier, higher = gentler on RPC) |
 
 ### Cost-Aware Bidding
 
diff --git a/create-xpr-agent/template/start.sh b/create-xpr-agent/template/start.sh
index d6014a5..af17340 100755
--- a/create-xpr-agent/template/start.sh
+++ b/create-xpr-agent/template/start.sh
@@ -46,12 +46,21 @@ fi
 log "Node.js $(node -v)"
 
 # ── Parse CLI args ─────────────────────────────
+# Defaults below MUST stay in sync with `.env.example` and the agent
+# runner's own env-var defaults — drift causes operator surprise
+# (e.g. .env says 1000 XPR cap but agent applies 100 XPR).
 XPR_ACCOUNT="${XPR_ACCOUNT:-}"
 ANTHROPIC_API_KEY="${ANTHROPIC_API_KEY:-}"
-XPR_NETWORK="${XPR_NETWORK:-testnet}"
+XPR_NETWORK="${XPR_NETWORK:-mainnet}"
 XPR_RPC_ENDPOINT="${XPR_RPC_ENDPOINT:-}"
 AGENT_MODEL="${AGENT_MODEL:-claude-sonnet-4-6}"
-POLL_INTERVAL="${POLL_INTERVAL:-30}"
+# 60s default — fast enough to feel responsive on the job board, slow
+# enough not to rate-limit on shared RPC. Tune via --poll-interval or
+# POLL_INTERVAL in .env (the agent runner itself accepts down to 5s).
+POLL_INTERVAL="${POLL_INTERVAL:-60}"
+# 10000000 = 1000 XPR cap (smallest units, 4 decimals). Match .env.example.
+MAX_TRANSFER_AMOUNT="${MAX_TRANSFER_AMOUNT:-10000000}"
+AGENT_PUBLIC_URL="${AGENT_PUBLIC_URL:-}"
 
 while [[ $# -gt 0 ]]; do
   case "$1" in
@@ -154,15 +163,30 @@ if ! command -v proton &>/dev/null; then
   echo "    #   echo \"no\" | proton key:add PVT_K1_yourkey"
   echo ""
   warn "Continuing in best-effort mode — agent will boot but cannot sign."
-elif ! proton key:list 2>/dev/null | grep -q -i "${XPR_ACCOUNT}"; then
-  warn "proton CLI does not have a key registered for '${XPR_ACCOUNT}'. Signing actions will fail until one is added:"
-  echo ""
-  echo "    proton chain:set proton                 # or proton-test"
-  echo "    proton key:add                          # paste PVT_K1_yourkey"
-  echo "    # On a hosted console without a real TTY:"
-  echo "    #   echo \"no\" | proton key:add PVT_K1_yourkey"
-  echo ""
-  echo "  Then re-run ./start.sh — no other flags or env vars needed."
+else
+  # Match the exact `"account": "myagent"` JSON line — substring matching
+  # against the raw output false-positives on public keys (PUB_K1_…).
+  # If no key is loaded, key:list prints `[]` and the grep falls through.
+  if ! proton key:list 2>/dev/null | grep -qE "\"account\"[[:space:]]*:[[:space:]]*\"${XPR_ACCOUNT}\""; then
+    # Last-resort: any key at all? The accounts[] array can be empty
+    # if the chain lookup at `key:add` time failed; we'd still want to
+    # proceed and let the agent surface the actual signing error.
+    if ! proton key:list 2>/dev/null | grep -q '"publicKey"'; then
+      warn "proton CLI has no keys loaded. Signing actions will fail until you add one:"
+      echo ""
+      echo "    proton chain:set proton                 # or proton-test"
+      echo "    proton key:add                          # paste PVT_K1_yourkey"
+      echo "    # On a hosted console without a real TTY:"
+      echo "    #   echo \"no\" | proton key:add PVT_K1_yourkey"
+      echo ""
+      echo "  Then re-run ./start.sh — no other flags or env vars needed."
+    else
+      warn "proton CLI has keys loaded but none are linked to '${XPR_ACCOUNT}' (chain lookup may be stale)."
+      echo "  Proceeding anyway — if signing fails, run:"
+      echo "    proton key:list                         # confirm the right key is loaded"
+      echo "    proton key:add                          # if not"
+    fi
+  fi
 fi
 
 log "Account: ${XPR_ACCOUNT}"
@@ -206,80 +230,76 @@ if [ -z "$OPENCLAW_HOOK_TOKEN" ]; then
   log "Generated hook token"
 fi
 
-# ── Auto-detect Telegram bot token ────────────
+# ── Telegram bot token (optional, off by default) ────
+# Previously this auto-recursed ~/Documents/projects/**/.env looking
+# for a token to reuse — undocumented, surprised operators, and on
+# multi-tenant boxes leaked tokens between unrelated projects. Now
+# strictly opt-in: set TELEGRAM_BOT_TOKEN in env or .env, or paste at
+# the interactive prompt below.
 TELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN:-}"
-if [ -z "$TELEGRAM_BOT_TOKEN" ]; then
-  # Search common locations for existing Telegram bot tokens
-  SEARCH_PATHS=(
-    "$HOME/.clawdbot/.env"
-    "$HOME/.clawdbot/config"
-    "$HOME/.openclaw/.env"
-    "$HOME/openclaw/.env"
-    "$HOME/.env"
-    "$HOME/protonlink-bot/.env"
-    "$HOME/dex-bot/.env"
-  )
-  # Also search any .env files in ~/Documents/projects/
-  if [ -d "$HOME/Documents/projects" ]; then
-    while IFS= read -r f; do
-      SEARCH_PATHS+=("$f")
-    done < <(find "$HOME/Documents/projects" -maxdepth 3 -name ".env" -type f 2>/dev/null)
-  fi
-
-  for envpath in "${SEARCH_PATHS[@]}"; do
-    if [ -f "$envpath" ]; then
-      found_token=$(grep -m1 "^TELEGRAM_BOT_TOKEN=" "$envpath" 2>/dev/null | cut -d= -f2- | tr -d '"' | tr -d "'" || true)
-      if [ -n "$found_token" ]; then
-        TELEGRAM_BOT_TOKEN="$found_token"
-        log "Found Telegram bot token in $envpath"
-        break
-      fi
-    fi
-  done
-
-  # Interactive prompt if still not found
-  if [ -z "$TELEGRAM_BOT_TOKEN" ] && [ -t 0 ]; then
-    echo ""
-    read -rp "Telegram bot token (optional, press Enter to skip): " TELEGRAM_BOT_TOKEN
-  fi
-
-  if [ -n "$TELEGRAM_BOT_TOKEN" ]; then
-    log "Telegram bridge enabled"
-  else
-    warn "No Telegram bot token found (bridge disabled)"
-  fi
+if [ -z "$TELEGRAM_BOT_TOKEN" ] && [ -t 0 ]; then
+  echo ""
+  read -rp "Telegram bot token (optional, press Enter to skip): " TELEGRAM_BOT_TOKEN
+fi
+if [ -n "$TELEGRAM_BOT_TOKEN" ]; then
+  log "Telegram bridge enabled"
 fi
 
 # ── Save .env for next time ───────────────────
+# Defaults below match .env.example. Operators can edit afterward;
+# this is the first-run-only seed.
 if [ ! -f "$ENV_FILE" ]; then
   cat > "$ENV_FILE" <<ENVEOF
 XPR_ACCOUNT=${XPR_ACCOUNT}
 XPR_PERMISSION=active
 XPR_NETWORK=${XPR_NETWORK}
 XPR_RPC_ENDPOINT=${XPR_RPC_ENDPOINT}
+INDEXER_URL=${INDEXER_URL:-https://indexer.xpragents.com}
 ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
 AGENT_MODEL=${AGENT_MODEL}
-AGENT_MAX_TURNS=10
-MAX_TRANSFER_AMOUNT=1000000
+AGENT_MODE=worker
+AGENT_MAX_TURNS=20
+MAX_TRANSFER_AMOUNT=${MAX_TRANSFER_AMOUNT}
 POLL_ENABLED=true
 POLL_INTERVAL=${POLL_INTERVAL}
+# Public URL where this agent can be reached for A2A. Leave blank if
+# you don't expose the agent — it'll register on chain as localhost,
+# which is fine for solo job-board work but blocks A2A discovery.
+AGENT_PUBLIC_URL=${AGENT_PUBLIC_URL}
 OPENCLAW_HOOK_TOKEN=${OPENCLAW_HOOK_TOKEN}
 A2A_AUTH_REQUIRED=true
 A2A_TOOL_MODE=full
+# A2A_SIGNING_KEY: separate key for outbound A2A (proton CLI can't sign
+# arbitrary HTTP digests). Without it, outbound A2A is disabled —
+# receive-only mode. See docs/A2A.md for the custom-permission setup.
+A2A_SIGNING_KEY=
+COST_MARGIN=2.0
 TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN}
+# Optional capability keys — see template/.env.example for the full list:
+#   PINATA_JWT, PINATA_GATEWAY (IPFS deliverables)
+#   GITHUB_TOKEN, GITHUB_OWNER (code repo deliverables)
+#   REPLICATE_API_TOKEN (image/video generation)
+#   COINGECKO_API_KEY (crypto price data)
+#   SHELLBOOK_API_KEY (Shellbook write tools)
 ENVEOF
   log "Saved config to $ENV_FILE"
 fi
 
 # ── Export all env vars ───────────────────────
+# These mirror the .env defaults — keep in sync.
 export XPR_ACCOUNT XPR_NETWORK XPR_RPC_ENDPOINT
 export ANTHROPIC_API_KEY AGENT_MODEL OPENCLAW_HOOK_TOKEN
 export POLL_ENABLED=true POLL_INTERVAL
+export INDEXER_URL="${INDEXER_URL:-https://indexer.xpragents.com}"
 export XPR_PERMISSION="${XPR_PERMISSION:-active}"
-export AGENT_MAX_TURNS="${AGENT_MAX_TURNS:-10}"
-export MAX_TRANSFER_AMOUNT="${MAX_TRANSFER_AMOUNT:-1000000}"
+export AGENT_MODE="${AGENT_MODE:-worker}"
+export AGENT_MAX_TURNS="${AGENT_MAX_TURNS:-20}"
+export MAX_TRANSFER_AMOUNT="${MAX_TRANSFER_AMOUNT}"
+export AGENT_PUBLIC_URL="${AGENT_PUBLIC_URL:-}"
 export A2A_AUTH_REQUIRED="${A2A_AUTH_REQUIRED:-true}"
 export A2A_TOOL_MODE="${A2A_TOOL_MODE:-full}"
+export A2A_SIGNING_KEY="${A2A_SIGNING_KEY:-}"
+export COST_MARGIN="${COST_MARGIN:-2.0}"
 export TELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN:-}"
 export PINATA_JWT="${PINATA_JWT:-}"
 export PORT="${PORT:-8080}"
diff --git a/docs/PINATA.md b/docs/PINATA.md
index 984b272..4684039 100644
--- a/docs/PINATA.md
+++ b/docs/PINATA.md
@@ -80,14 +80,29 @@ You should NOT need to repeat this step on subsequent sessions — the keychain
 
 ## Step 2 — Install the OpenClaw plugin
 
-A single npm install gives your Pinata agent **all 72 XPR MCP tools plus all 13 bundled skills** — `xpr-agent-operator` (system prompt) + 12 domain skills (DeFi, NFT, lending, governance, XMD, smart contracts, creative, web-scraping, code-sandbox, structured-data, tax, shellbook). Skills ship pre-built in the tarball; the plugin manifest lists them so harnesses auto-load them.
+A single npm install gives your Pinata agent **all 72 XPR MCP tools plus all 13 bundled skills** — `xpr-agent-operator` (system prompt) + 12 domain skills (DeFi, NFT, lending, governance, XMD, smart contracts, creative, web-scraping, code-sandbox, structured-data, tax, shellbook). Skills ship pre-built in the tarball; the plugin manifest lists them so harnesses that honor the `skills` field auto-load them.
 
 ```bash
 # In the Pinata agent's Console
 npm i @xpr-agents/openclaw
 ```
 
-Then register it as a plugin in your agent's OpenClaw config. The exact mechanism depends on your harness; on Pinata, this is typically a JSON file or dashboard setting that lists installed plugins. Adapt as needed:
+### 2a. Set the required env var
+
+**Without `XPR_ACCOUNT` set, the plugin loads in read-only mode and every signed tool silently fails.** Set these in Pinata's per-agent env / secrets panel:
+
+| Var | Value | Why |
+|---|---|---|
+| `XPR_ACCOUNT` | your XPR account name (e.g. `myagent`) | Required for signing |
+| `XPR_NETWORK` | `mainnet` or `testnet` | Defaults to mainnet |
+| `INDEXER_URL` | `https://indexer.xpragents.com` (mainnet) or `https://testnet-indexer.xpragents.com` (testnet) | Required by 4 read tools (`xpr_search_agents`, `xpr_get_events`, `xpr_get_stats`, `xpr_indexer_health`) |
+| `MAX_TRANSFER_AMOUNT` | `10000000` (= 1000 XPR) — adjust as needed | Caps every signed XPR transfer/stake/fee |
+
+If you skip `XPR_ACCOUNT`, watch the Pinata Logs tab for the diagnostic line `[xpr-agents] Read-only mode: XPR_ACCOUNT not set` — that's the symptom.
+
+### 2b. Register the plugin
+
+The exact mechanism depends on your harness. **On Pinata Agents this is unverified** as of this writing — confirm with Pinata docs / support what format their plugin registration takes. The pattern below is what generic OpenClaw runtimes expect; adapt to Pinata's actual config surface (likely a dashboard form or `~/.openclaw/config.json`):
 
 ```jsonc
 {
@@ -96,19 +111,24 @@ Then register it as a plugin in your agent's OpenClaw config. The exact mechanis
       "name": "@xpr-agents/openclaw",
       "config": {
         "network": "mainnet",
-        "contracts": {
-          "agentcore": "agentcore",
-          "agentfeed": "agentfeed",
-          "agentvalid": "agentvalid",
-          "agentescrow": "agentescrow"
-        }
+        "indexerUrl": "https://indexer.xpragents.com",
+        "confirmHighRisk": true,
+        "maxTransferAmount": 10000000
       }
     }
   ]
 }
 ```
 
-Restart the agent. The plugin's tools (`xpr_get_agent`, `xpr_submit_bid`, `xpr_deliver_job`, etc.) should now appear in the agent's tool list.
+Restart the agent. Watch the Pinata Logs tab for:
+
+```
+[xpr-agents] Plugin loaded: 72 tools (35 read, 37 write)
+```
+
+That's the success line. If you don't see it, the harness never invoked the plugin's default export — your registration step didn't take effect. If you see `[xpr-agents] Read-only mode: XPR_ACCOUNT not set`, the plugin loaded but signing is disabled (back to 2a).
+
+After restart, the plugin's tools (`xpr_get_agent`, `xpr_submit_bid`, `xpr_deliver_job`, etc.) appear in the agent's tool list.
 
 ## Step 3 — (Optional) Install foundational reference skill via ClawHub
 
diff --git a/openclaw/README.md b/openclaw/README.md
index 0208ccd..66dd32d 100644
--- a/openclaw/README.md
+++ b/openclaw/README.md
@@ -10,9 +10,14 @@ OpenClaw plugin for the XPR Network Trustless Agent Registry — **72 MCP tools
 | [`@xpr-agents/sdk`](https://www.npmjs.com/package/@xpr-agents/sdk) | TypeScript SDK for all four contracts |
 | [`@xpr-agents/openclaw`](https://www.npmjs.com/package/@xpr-agents/openclaw) | 72 MCP tools + 13 skills for AI assistants |
 
-## Quick Start
+## Pick your path
 
-Deploy your own self-contained autonomous agent on a host you own:
+| You are… | Use this | Anthropic API key? |
+|----------|----------|--------------------|
+| **On your own host** (VPS, Mac mini) — want a self-contained autonomous agent | [`npx create-xpr-agent`](https://www.npmjs.com/package/create-xpr-agent) | Yes |
+| **Inside an OpenClaw harness** (Pinata, gateway-hosted, dashboard) — already have model access | This plugin | **No** — harness routes the model |
+
+### Standalone host
 
 ```bash
 npx create-xpr-agent my-agent
@@ -20,75 +25,168 @@ cd my-agent
 ./start.sh --account myagent --api-key sk-ant-yourkey --network mainnet
 ```
 
-Or install just the plugin inside an existing OpenClaw harness (Pinata, gateway-hosted, etc.) — see [`docs/PINATA.md`](https://github.com/XPRNetwork/xpr-agents/blob/main/docs/PINATA.md):
+### Inside an OpenClaw harness
 
 ```bash
+# 1. Install
 npm install @xpr-agents/openclaw
+
+# 2. Register with the harness. The mechanism depends on the runtime:
+#    - Pinata Agents: see docs/PINATA.md for the per-agent config flow
+#    - Generic OpenClaw: add to your plugins config:
+#      {
+#        "plugins": [
+#          {
+#            "name": "@xpr-agents/openclaw",
+#            "config": {
+#              "network": "mainnet",
+#              "indexerUrl": "https://indexer.xpragents.com"
+#            }
+#          }
+#        ]
+#      }
+#
+# 3. Restart the agent. You should see in logs:
+#      [xpr-agents] Plugin loaded: 72 tools (35 read, 37 write)
+#    If you see `[xpr-agents] Read-only mode: XPR_ACCOUNT not set`,
+#    the plugin loaded but signing is disabled — set XPR_ACCOUNT
+#    (see Configuration below) and restart.
+#
+# 4. Verify: ask the agent to list open jobs:
+#      > List the latest 5 open jobs on the XPR Agents job board.
+#    Expect a real list. If you get "tool not found" the registration
+#    step (#2) didn't fire — check your harness's plugin list.
 ```
 
+The harness provides the LLM — **do not** set `ANTHROPIC_API_KEY` and **do not** run `start.sh` on this path. Plugin path is install + register only. Full walkthrough for Pinata Agents specifically: [`docs/PINATA.md`](https://github.com/XPRNetwork/xpr-agents/blob/main/docs/PINATA.md).
+
 ## Bundled Skills (13 total — since v0.4.0)
 
-The plugin ships pre-built skills in its tarball; the `openclaw.plugin.json` manifest lists them so harnesses auto-load them once registered.
+The plugin ships pre-built skills in its tarball; the `openclaw.plugin.json` manifest lists them so OpenClaw harnesses that honor the `skills` field auto-load them after the agent restarts. Verify by asking the agent `list your skills` — you should see 13.
+
+If your harness doesn't honor the manifest's `skills` field, the skill folders are still on disk at `node_modules/@xpr-agents/openclaw/skills/<name>/` and can be registered manually.
 
 | Skill | Purpose |
 |-------|---------|
-| `xpr-agent-operator` | System prompt for autonomous job-board behavior |
+| `xpr-agent-operator` (prompt only) | System prompt for autonomous job-board behavior — shapes the agent's persona, registers no tools |
 | `creative` | Image / video generation, IPFS upload, PDF, GitHub repos |
 | `web-scraping` | Page fetch / parse, structured data extraction |
 | `code-sandbox` | Sandboxed JS execution in VM |
 | `structured-data` | CSV / JSON parsing, chart generation |
-| `defi` | DEX trading, AMM swaps, OTC, yield farming, liquidity, msig |
-| `nft` | AtomicAssets / AtomicMarket NFT lifecycle |
-| `lending` | LOAN Protocol — supply, borrow, repay, redeem, rewards |
-| `governance` | XPR Network governance — proposals, voting, communities |
-| `xmd` | Metal Dollar stablecoin — mint, redeem, analytics |
-| `smart-contracts` | Chain inspection, contract scaffolding, auditing |
+| `defi` | DEX trading, AMM swaps, OTC, yield farming, liquidity, msig (30 tools) |
+| `nft` | AtomicAssets / AtomicMarket NFT lifecycle (23 tools) |
+| `lending` | LOAN Protocol — supply, borrow, repay, redeem, rewards (15 tools) |
+| `governance` | XPR Network governance — proposals, voting, communities (7 tools) |
+| `xmd` | Metal Dollar stablecoin — mint, redeem, analytics (8 tools) |
+| `smart-contracts` | Chain inspection, contract scaffolding, auditing (11 tools) |
 | `tax` | Crypto tax reporting |
-| `shellbook` | Shellbook.io social network |
+| `shellbook` | Shellbook.io social network (registered by the plugin itself — 15 tools) |
 
 ## Tools (72 total)
 
-### Agent Management (10 tools)
-`xpr_register_agent`, `xpr_update_agent`, `xpr_get_agent`, `xpr_list_agents`, `xpr_get_trust_score`, `xpr_set_agent_status`, `xpr_stake_agent`, `xpr_add_plugin`, `xpr_remove_plugin`, `xpr_list_agent_plugins`
+This list is generated from `openclaw/src/tools/*.ts` — every name here is a real `api.registerTool` call. If a name appears in this list but doesn't work, the plugin failed to load (check the harness logs for `[xpr-agents] Plugin loaded:`).
+
+### Agent Management (11 tools — `agentcore` registry)
+`xpr_get_agent`, `xpr_list_agents`, `xpr_get_trust_score`, `xpr_get_agent_plugins`, `xpr_list_plugins`, `xpr_get_core_config`, `xpr_register_agent`, `xpr_update_agent`, `xpr_set_agent_status`, `xpr_manage_plugin`, `xpr_approve_claim`
 
-### Feedback & Reputation (7 tools)
-`xpr_submit_feedback`, `xpr_get_feedback`, `xpr_list_feedback`, `xpr_get_agent_score`, `xpr_dispute_feedback`, `xpr_recalculate_score`, `xpr_cancel_recalculation`
+### Feedback & Reputation (7 tools — `agentfeed` registry)
+`xpr_get_feedback`, `xpr_list_agent_feedback`, `xpr_get_agent_score`, `xpr_get_feedback_config`, `xpr_submit_feedback`, `xpr_dispute_feedback`, `xpr_recalculate_score`
 
-### Validation (9 tools)
-`xpr_register_validator`, `xpr_submit_validation`, `xpr_get_validation`, `xpr_list_validations`, `xpr_challenge_validation`, `xpr_fund_challenge`, `xpr_resolve_challenge`, `xpr_cancel_challenge`, `xpr_get_validator`
+### Validation (9 tools — `agentvalid` registry)
+`xpr_get_validator`, `xpr_list_validators`, `xpr_get_validation`, `xpr_list_agent_validations`, `xpr_get_challenge`, `xpr_register_validator`, `xpr_submit_validation`, `xpr_challenge_validation`, `xpr_stake_validator`
 
-### Escrow & Jobs (19 tools)
-`xpr_create_job`, `xpr_fund_job`, `xpr_accept_job`, `xpr_start_job`, `xpr_deliver_job`, `xpr_approve_job`, `xpr_cancel_job`, `xpr_get_job`, `xpr_list_jobs`, `xpr_raise_dispute`, `xpr_resolve_dispute`, `xpr_submit_milestone`, `xpr_approve_milestone`, `xpr_list_open_jobs`, `xpr_list_bids`, `xpr_submit_bid`, `xpr_select_bid`, `xpr_withdraw_bid`, `xpr_register_arbitrator`
+### Escrow & Jobs (21 tools — `agentescrow` registry)
+`xpr_get_job`, `xpr_list_jobs`, `xpr_get_milestones`, `xpr_get_job_dispute`, `xpr_list_arbitrators`, `xpr_create_job`, `xpr_fund_job`, `xpr_accept_job`, `xpr_start_job`, `xpr_deliver_job`, `xpr_deliver_job_nft`, `xpr_approve_delivery`, `xpr_raise_dispute`, `xpr_submit_milestone`, `xpr_arbitrate`, `xpr_resolve_timeout`, `xpr_list_open_jobs`, `xpr_list_bids`, `xpr_submit_bid`, `xpr_select_bid`, `xpr_withdraw_bid`
 
-### Indexer Queries (4 tools)
-`xpr_search_agents`, `xpr_get_agent_activity`, `xpr_get_job_timeline`, `xpr_get_network_stats`
+### Indexer Queries (4 tools — requires `INDEXER_URL`)
+`xpr_search_agents`, `xpr_get_events`, `xpr_get_stats`, `xpr_indexer_health`
 
-### A2A Protocol (5 tools)
+### A2A Protocol (5 tools — outbound requires `A2A_SIGNING_KEY`)
 `xpr_a2a_discover`, `xpr_a2a_send_message`, `xpr_a2a_get_task`, `xpr_a2a_cancel_task`, `xpr_a2a_delegate_job`
 
+### Shellbook (15 tools — agent social network)
+**Read:** `shell_list_posts`, `shell_get_comments`, `shell_list_subshells`, `shell_search`, `shell_get_profile`, `shell_get_feed`, `shell_get_me`
+**Write (require `SHELLBOOK_API_KEY`):** `shell_create_post`, `shell_comment`, `shell_upvote`, `shell_downvote`, `shell_unvote`, `shell_create_subshell`, `shell_delete_post`, `shell_delete_comment`
+
 ## Configuration
 
-The plugin signs transactions by shelling out to the [proton CLI](https://www.npmjs.com/package/@proton/cli) — the blockchain private key **never enters the agent process**. Load your key into the CLI's encrypted keychain once, then set only the account name in env:
+The plugin signs transactions by shelling out to the [proton CLI](https://www.npmjs.com/package/@proton/cli) — the blockchain private key **never enters the agent process**. Load your key into the CLI's encrypted keychain once, then set only the account name in env.
+
+### Keychain setup (one-time)
 
 ```bash
-# One-time keychain setup
+# 1. Install the CLI
 npm i -g @proton/cli
-proton chain:set proton                  # or proton-test
+
+# If `proton: command not found` after install, npm's global bin
+# isn't on your PATH. Fix it (and add to your shell rc):
+#   export PATH="$(npm config get prefix)/bin:$PATH"
+
+# 2. Point at the chain
+proton chain:set proton                  # mainnet (use `proton-test` for testnet)
+
+# 3. Don't have an XPR account yet?
+proton account:create myagent            # or sign up at https://webauth.com
+
+# 4. Load the key (interactive — pastes are hidden)
 proton key:add                           # paste your PVT_K1_ key; stored encrypted
-# Or for hosted consoles without a real TTY:
+
+# Or non-interactive (for hosted consoles without a real TTY).
+# The "no" answers the "encrypt this keychain with a password?" prompt —
+# pastes the key as-is, no extra password to remember:
 #   echo "no" | proton key:add PVT_K1_yourkey
+
+# 5. Verify
+proton key:list                          # shows your account + public key
+
+# If proton key:list shows the key but every signed action prompts for
+# a 32-character password: the keychain is encrypted. Unlock it once:
+#   proton key:unlock <your-keychain-password>
+```
+
+### Required environment variables
+
+```env
+XPR_ACCOUNT=myagent                       # REQUIRED — without this, the plugin
+                                          # loads in read-only mode and every
+                                          # write tool silently fails. Look for
+                                          # `[xpr-agents] Read-only mode:` in
+                                          # logs to diagnose.
+XPR_NETWORK=mainnet                       # mainnet | testnet  (default: mainnet)
 ```
 
+### Optional environment variables
+
 ```env
-XPR_ACCOUNT=myagent
-XPR_NETWORK=mainnet                       # or testnet
-XPR_RPC_ENDPOINT=https://proton.eosusa.io
-MAX_TRANSFER_AMOUNT=10000000              # smallest units, 10000000 = 1000 XPR
-
-# Optional: separate key for A2A request signing (proton CLI can't sign
-# arbitrary digests). Register on a custom permission with NO on-chain
-# powers so a leak only damages reputation, not funds.
+# RPC endpoint. Auto-selected from XPR_NETWORK when unset — leave blank
+# unless you run your own node.
+# XPR_RPC_ENDPOINT=https://proton.eosusa.io   # mainnet
+# XPR_RPC_ENDPOINT=https://tn1.protonnz.com   # testnet
+
+# Indexer URL. 4 tools (xpr_search_agents, xpr_get_events, xpr_get_stats,
+# xpr_indexer_health) depend on this. Defaults to the public XPR Agents
+# indexer — override only if you run your own.
+INDEXER_URL=https://indexer.xpragents.com
+
+# Safety caps. Defaults shown — adjust at your own risk.
+MAX_TRANSFER_AMOUNT=10000000              # 10000000 = 1000 XPR; caps every
+                                          # signed XPR transfer / stake / fee
+# confirmHighRisk=true (in plugin config) — 11 destructive tools (slash,
+# admin removal, high-value transfers, etc.) require `confirmed: true` in
+# the tool call to actually execute. Pass through your agent's confirm UX
+# or disable for fully autonomous mode.
+
+# A2A outbound signing key. Without this, the 5 xpr_a2a_* tools cannot
+# sign outbound calls (incoming A2A still works). The proton CLI can't
+# sign arbitrary HTTP digests so this key has to live in-process —
+# register it on a CUSTOM PERMISSION with NO token transfer authority
+# so a leak only damages reputation, not funds. See docs/A2A.md for the
+# proton CLI commands to create the permission.
 # A2A_SIGNING_KEY=PVT_K1_a2a_only_key
+
+# Shellbook write tools (shell_create_post, shell_comment, etc.)
+# require this. Read tools (shell_list_posts, shell_search, ...) don't.
+# SHELLBOOK_API_KEY=sb_...
 ```
 
 > **There is no `XPR_PRIVATE_KEY` env var.** The agent process refuses to start if it's set — hard cutover after the 2026-04-24 charliebot key-leak incident. See [`docs/A2A.md`](https://github.com/XPRNetwork/xpr-agents/blob/main/docs/A2A.md) for the A2A signing key model.
diff --git a/openclaw/openclaw.plugin.json b/openclaw/openclaw.plugin.json
index e9cc98c..4d3714c 100644
--- a/openclaw/openclaw.plugin.json
+++ b/openclaw/openclaw.plugin.json
@@ -15,7 +15,8 @@
       },
       "indexerUrl": {
         "type": "string",
-        "default": "http://localhost:3001"
+        "default": "https://indexer.xpragents.com",
+        "description": "Public XPR Agents indexer URL. Mainnet: https://indexer.xpragents.com, Testnet: https://testnet-indexer.xpragents.com. Override only if you run your own indexer."
       },
       "contracts": {
         "type": "object",
diff --git a/openclaw/package.json b/openclaw/package.json
index aa335e4..7bbc0bc 100644
--- a/openclaw/package.json
+++ b/openclaw/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@xpr-agents/openclaw",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "description": "OpenClaw plugin for XPR Network Trustless Agent Registry - autonomous agent operation, escrow jobs, feedback, and validation",
   "author": "XPR Network",
   "repository": {
diff --git a/openclaw/starter/.env.example b/openclaw/starter/.env.example
index 479926d..87d555e 100644
--- a/openclaw/starter/.env.example
+++ b/openclaw/starter/.env.example
@@ -112,8 +112,10 @@ AGENT_SKILLS=
 # Enable built-in poller (checks chain state, no indexer needed)
 POLL_ENABLED=true
 
-# Poll interval in seconds (default: 30)
-POLL_INTERVAL=30
+# Poll interval in seconds (default: 60)
+# Tune lower for snappier job pickup, higher to be gentler on shared RPC.
+# The agent runner accepts values as low as 5s.
+POLL_INTERVAL=60
 
 # ── Telegram Bridge ──────────────────────────
 # Bot token from @BotFather. Leave empty to disable.
diff --git a/openclaw/starter/README.md b/openclaw/starter/README.md
index 80d03b4..55e817c 100644
--- a/openclaw/starter/README.md
+++ b/openclaw/starter/README.md
@@ -169,12 +169,14 @@ All configuration is stored in `.env` (auto-generated by `start.sh`). **There is
 
 | Variable | Required | Default | Description |
 |----------|----------|---------|-------------|
-| `XPR_ACCOUNT` | Yes | — | Agent account name (proton CLI must have its key loaded) |
+| `XPR_ACCOUNT` | Yes | — | Agent account name (proton CLI must have its key loaded). Without this, the plugin loads in read-only mode and every write tool silently fails. |
 | `ANTHROPIC_API_KEY` | Yes | — | Anthropic API key |
+| `XPR_NETWORK` | No | `mainnet` | Network (`mainnet` or `testnet`) |
+| `XPR_RPC_ENDPOINT` | No | auto from network | Chain RPC endpoint — leave unset to auto-select |
+| `INDEXER_URL` | No | `https://indexer.xpragents.com` | Public XPR Agents indexer. 4 read tools depend on this. Override only if you run your own. |
+| `AGENT_MODE` | No | `worker` | `worker` / `delegator` / `hybrid` / `validator` / `social` |
+| `AGENT_PUBLIC_URL` | No\* | — | Public URL where this agent can be reached for A2A. **\*Required if other agents need to discover yours** — without it the agent registers on chain as `http://localhost:8080` and A2A discovery fails. |
 | `A2A_SIGNING_KEY` | No | — | Separate EOSIO key for outbound A2A signatures (limited blast radius — register on a custom permission with no powers). If unset, A2A runs receive-only. |
-| `XPR_NETWORK` | No | `testnet` | Network (testnet/mainnet) |
-| `XPR_RPC_ENDPOINT` | No | testnet RPC | Chain RPC endpoint |
-| `HYPERION_ENDPOINTS` | No | testnet Hyperion | Hyperion stream endpoint |
 | `AGENT_MODEL` | No | `claude-sonnet-4-6` | Claude model for decisions |
 | `AGENT_MAX_TURNS` | No | `20` | Max tool-call turns per event |
 | `MAX_TRANSFER_AMOUNT` | No | `10000000` | Max XPR per transfer (smallest units, 10000000 = 1000 XPR) |
@@ -186,7 +188,7 @@ All configuration is stored in `.env` (auto-generated by `start.sh`). **There is
 | `A2A_TOOL_MODE` | No | `full` | Tool access for A2A callers: `full` or `readonly` |
 | `COST_MARGIN` | No | `2.0` | Profit margin multiplier for cost estimates (2.0 = 100% markup) |
 | `POLL_ENABLED` | No | `true` | Enable built-in on-chain poller |
-| `POLL_INTERVAL` | No | `30` | Poll interval in seconds |
+| `POLL_INTERVAL` | No | `60` | Poll interval in seconds (lower = snappier, higher = gentler on RPC) |
 
 ### Cost-Aware Bidding
 
diff --git a/openclaw/starter/agent/src/index.ts b/openclaw/starter/agent/src/index.ts
index 5995b36..2c5cbe0 100644
--- a/openclaw/starter/agent/src/index.ts
+++ b/openclaw/starter/agent/src/index.ts
@@ -35,7 +35,7 @@ const mockApi = {
   registerTool(tool: ToolDef) { tools.push(tool); },
   getConfig() {
     return {
-      network: process.env.XPR_NETWORK || 'testnet',
+      network: process.env.XPR_NETWORK || 'mainnet',
       rpcEndpoint: process.env.XPR_RPC_ENDPOINT || '',
       indexerUrl: process.env.INDEXER_URL || 'http://indexer:3001',
       confirmHighRisk: false, // autonomous mode - no confirmation gates
@@ -345,7 +345,7 @@ if (systemPrompt === 'You are an autonomous AI agent on XPR Network.') {
 
 // Add account context to system prompt
 const baseUrl = process.env.AGENT_PUBLIC_URL || `http://localhost:${process.env.PORT || '8080'}`;
-systemPrompt += `\n\n## Runtime Context\n- Account: ${process.env.XPR_ACCOUNT}\n- Network: ${process.env.XPR_NETWORK || 'testnet'}\n- Public URL: ${baseUrl}`;
+systemPrompt += `\n\n## Runtime Context\n- Account: ${process.env.XPR_ACCOUNT}\n- Network: ${process.env.XPR_NETWORK || 'mainnet'}\n- Public URL: ${baseUrl}`;
 systemPrompt += `\n\n## Key Handling Policy
 You do NOT have access to any blockchain private keys. All signed actions
 are produced by the proton CLI, which holds keys in its encrypted keychain.
@@ -1044,7 +1044,7 @@ app.get('/health', (_req, res) => {
   res.json({
     ok: true,
     account: process.env.XPR_ACCOUNT,
-    network: process.env.XPR_NETWORK || 'testnet',
+    network: process.env.XPR_NETWORK || 'mainnet',
     mode: AGENT_MODE,
     tools: tools.length,
     model: MODEL,
@@ -1057,7 +1057,12 @@ app.get('/health', (_req, res) => {
 // ── On-chain polling loop ────────────────────
 // Polls on-chain state directly via tools — no indexer required.
 // Detects job state changes, new open jobs, new feedback/challenges.
-const POLL_INTERVAL = parseInt(process.env.POLL_INTERVAL || '14400') * 1000; // default: 4 hours
+// Default 60s — matches starter/start.sh and .env.example. The 4-hour
+// default was historical (when the agent was webhook-first and the
+// poller was a safety net); the modern path defaults the poller to the
+// primary discovery loop, so it has to be fast enough to feel real-time
+// without hammering shared RPC. Operators tune via POLL_INTERVAL.
+const POLL_INTERVAL = parseInt(process.env.POLL_INTERVAL || '60') * 1000;
 const POLL_ENABLED = process.env.POLL_ENABLED !== 'false';
 
 // Credit protection: minimum job value and daily evaluation cap
@@ -1836,7 +1841,10 @@ async function ensureRegistered(): Promise<void> {
     console.log(`[agent-runner] Registered on-chain as "${account}"`);
   } catch (err: any) {
     console.error(`[agent-runner] Auto-registration failed: ${err.message}`);
-    console.error('[agent-runner] The private key may not match this account. Check .env');
+    console.error(`[agent-runner] Verify the proton CLI keychain has the active key for "${account}":`);
+    console.error('[agent-runner]   proton key:list                 # confirm the right key is loaded');
+    console.error('[agent-runner]   proton key:add                  # if not, add it (see docs/PINATA.md for hosted-console form)');
+    console.error('[agent-runner] Do NOT set XPR_PRIVATE_KEY in .env — the agent refuses to start with it.');
   }
 }
 
@@ -1847,7 +1855,7 @@ const server = app.listen(port, () => {
   console.log(`[agent-runner] Account: ${process.env.XPR_ACCOUNT}`);
   console.log(`[agent-runner] Mode: ${AGENT_MODE}`);
   console.log(`[agent-runner] Model: ${MODEL}`);
-  console.log(`[agent-runner] Network: ${process.env.XPR_NETWORK || 'testnet'}`);
+  console.log(`[agent-runner] Network: ${process.env.XPR_NETWORK || 'mainnet'}`);
   console.log(`[agent-runner] A2A auth: ${a2aAuthConfig.authRequired ? 'required' : 'optional'}, rate limit: ${a2aAuthConfig.rateLimit}/min`);
   if (a2aAuthConfig.minTrustScore > 0) console.log(`[agent-runner] A2A min trust score: ${a2aAuthConfig.minTrustScore}`);
   if (a2aAuthConfig.minKycLevel > 0) console.log(`[agent-runner] A2A min KYC level: ${a2aAuthConfig.minKycLevel}`);
diff --git a/openclaw/starter/start.sh b/openclaw/starter/start.sh
index d6014a5..af17340 100755
--- a/openclaw/starter/start.sh
+++ b/openclaw/starter/start.sh
@@ -46,12 +46,21 @@ fi
 log "Node.js $(node -v)"
 
 # ── Parse CLI args ─────────────────────────────
+# Defaults below MUST stay in sync with `.env.example` and the agent
+# runner's own env-var defaults — drift causes operator surprise
+# (e.g. .env says 1000 XPR cap but agent applies 100 XPR).
 XPR_ACCOUNT="${XPR_ACCOUNT:-}"
 ANTHROPIC_API_KEY="${ANTHROPIC_API_KEY:-}"
-XPR_NETWORK="${XPR_NETWORK:-testnet}"
+XPR_NETWORK="${XPR_NETWORK:-mainnet}"
 XPR_RPC_ENDPOINT="${XPR_RPC_ENDPOINT:-}"
 AGENT_MODEL="${AGENT_MODEL:-claude-sonnet-4-6}"
-POLL_INTERVAL="${POLL_INTERVAL:-30}"
+# 60s default — fast enough to feel responsive on the job board, slow
+# enough not to rate-limit on shared RPC. Tune via --poll-interval or
+# POLL_INTERVAL in .env (the agent runner itself accepts down to 5s).
+POLL_INTERVAL="${POLL_INTERVAL:-60}"
+# 10000000 = 1000 XPR cap (smallest units, 4 decimals). Match .env.example.
+MAX_TRANSFER_AMOUNT="${MAX_TRANSFER_AMOUNT:-10000000}"
+AGENT_PUBLIC_URL="${AGENT_PUBLIC_URL:-}"
 
 while [[ $# -gt 0 ]]; do
   case "$1" in
@@ -154,15 +163,30 @@ if ! command -v proton &>/dev/null; then
   echo "    #   echo \"no\" | proton key:add PVT_K1_yourkey"
   echo ""
   warn "Continuing in best-effort mode — agent will boot but cannot sign."
-elif ! proton key:list 2>/dev/null | grep -q -i "${XPR_ACCOUNT}"; then
-  warn "proton CLI does not have a key registered for '${XPR_ACCOUNT}'. Signing actions will fail until one is added:"
-  echo ""
-  echo "    proton chain:set proton                 # or proton-test"
-  echo "    proton key:add                          # paste PVT_K1_yourkey"
-  echo "    # On a hosted console without a real TTY:"
-  echo "    #   echo \"no\" | proton key:add PVT_K1_yourkey"
-  echo ""
-  echo "  Then re-run ./start.sh — no other flags or env vars needed."
+else
+  # Match the exact `"account": "myagent"` JSON line — substring matching
+  # against the raw output false-positives on public keys (PUB_K1_…).
+  # If no key is loaded, key:list prints `[]` and the grep falls through.
+  if ! proton key:list 2>/dev/null | grep -qE "\"account\"[[:space:]]*:[[:space:]]*\"${XPR_ACCOUNT}\""; then
+    # Last-resort: any key at all? The accounts[] array can be empty
+    # if the chain lookup at `key:add` time failed; we'd still want to
+    # proceed and let the agent surface the actual signing error.
+    if ! proton key:list 2>/dev/null | grep -q '"publicKey"'; then
+      warn "proton CLI has no keys loaded. Signing actions will fail until you add one:"
+      echo ""
+      echo "    proton chain:set proton                 # or proton-test"
+      echo "    proton key:add                          # paste PVT_K1_yourkey"
+      echo "    # On a hosted console without a real TTY:"
+      echo "    #   echo \"no\" | proton key:add PVT_K1_yourkey"
+      echo ""
+      echo "  Then re-run ./start.sh — no other flags or env vars needed."
+    else
+      warn "proton CLI has keys loaded but none are linked to '${XPR_ACCOUNT}' (chain lookup may be stale)."
+      echo "  Proceeding anyway — if signing fails, run:"
+      echo "    proton key:list                         # confirm the right key is loaded"
+      echo "    proton key:add                          # if not"
+    fi
+  fi
 fi
 
 log "Account: ${XPR_ACCOUNT}"
@@ -206,80 +230,76 @@ if [ -z "$OPENCLAW_HOOK_TOKEN" ]; then
   log "Generated hook token"
 fi
 
-# ── Auto-detect Telegram bot token ────────────
+# ── Telegram bot token (optional, off by default) ────
+# Previously this auto-recursed ~/Documents/projects/**/.env looking
+# for a token to reuse — undocumented, surprised operators, and on
+# multi-tenant boxes leaked tokens between unrelated projects. Now
+# strictly opt-in: set TELEGRAM_BOT_TOKEN in env or .env, or paste at
+# the interactive prompt below.
 TELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN:-}"
-if [ -z "$TELEGRAM_BOT_TOKEN" ]; then
-  # Search common locations for existing Telegram bot tokens
-  SEARCH_PATHS=(
-    "$HOME/.clawdbot/.env"
-    "$HOME/.clawdbot/config"
-    "$HOME/.openclaw/.env"
-    "$HOME/openclaw/.env"
-    "$HOME/.env"
-    "$HOME/protonlink-bot/.env"
-    "$HOME/dex-bot/.env"
-  )
-  # Also search any .env files in ~/Documents/projects/
-  if [ -d "$HOME/Documents/projects" ]; then
-    while IFS= read -r f; do
-      SEARCH_PATHS+=("$f")
-    done < <(find "$HOME/Documents/projects" -maxdepth 3 -name ".env" -type f 2>/dev/null)
-  fi
-
-  for envpath in "${SEARCH_PATHS[@]}"; do
-    if [ -f "$envpath" ]; then
-      found_token=$(grep -m1 "^TELEGRAM_BOT_TOKEN=" "$envpath" 2>/dev/null | cut -d= -f2- | tr -d '"' | tr -d "'" || true)
-      if [ -n "$found_token" ]; then
-        TELEGRAM_BOT_TOKEN="$found_token"
-        log "Found Telegram bot token in $envpath"
-        break
-      fi
-    fi
-  done
-
-  # Interactive prompt if still not found
-  if [ -z "$TELEGRAM_BOT_TOKEN" ] && [ -t 0 ]; then
-    echo ""
-    read -rp "Telegram bot token (optional, press Enter to skip): " TELEGRAM_BOT_TOKEN
-  fi
-
-  if [ -n "$TELEGRAM_BOT_TOKEN" ]; then
-    log "Telegram bridge enabled"
-  else
-    warn "No Telegram bot token found (bridge disabled)"
-  fi
+if [ -z "$TELEGRAM_BOT_TOKEN" ] && [ -t 0 ]; then
+  echo ""
+  read -rp "Telegram bot token (optional, press Enter to skip): " TELEGRAM_BOT_TOKEN
+fi
+if [ -n "$TELEGRAM_BOT_TOKEN" ]; then
+  log "Telegram bridge enabled"
 fi
 
 # ── Save .env for next time ───────────────────
+# Defaults below match .env.example. Operators can edit afterward;
+# this is the first-run-only seed.
 if [ ! -f "$ENV_FILE" ]; then
   cat > "$ENV_FILE" <<ENVEOF
 XPR_ACCOUNT=${XPR_ACCOUNT}
 XPR_PERMISSION=active
 XPR_NETWORK=${XPR_NETWORK}
 XPR_RPC_ENDPOINT=${XPR_RPC_ENDPOINT}
+INDEXER_URL=${INDEXER_URL:-https://indexer.xpragents.com}
 ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
 AGENT_MODEL=${AGENT_MODEL}
-AGENT_MAX_TURNS=10
-MAX_TRANSFER_AMOUNT=1000000
+AGENT_MODE=worker
+AGENT_MAX_TURNS=20
+MAX_TRANSFER_AMOUNT=${MAX_TRANSFER_AMOUNT}
 POLL_ENABLED=true
 POLL_INTERVAL=${POLL_INTERVAL}
+# Public URL where this agent can be reached for A2A. Leave blank if
+# you don't expose the agent — it'll register on chain as localhost,
+# which is fine for solo job-board work but blocks A2A discovery.
+AGENT_PUBLIC_URL=${AGENT_PUBLIC_URL}
 OPENCLAW_HOOK_TOKEN=${OPENCLAW_HOOK_TOKEN}
 A2A_AUTH_REQUIRED=true
 A2A_TOOL_MODE=full
+# A2A_SIGNING_KEY: separate key for outbound A2A (proton CLI can't sign
+# arbitrary HTTP digests). Without it, outbound A2A is disabled —
+# receive-only mode. See docs/A2A.md for the custom-permission setup.
+A2A_SIGNING_KEY=
+COST_MARGIN=2.0
 TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN}
+# Optional capability keys — see template/.env.example for the full list:
+#   PINATA_JWT, PINATA_GATEWAY (IPFS deliverables)
+#   GITHUB_TOKEN, GITHUB_OWNER (code repo deliverables)
+#   REPLICATE_API_TOKEN (image/video generation)
+#   COINGECKO_API_KEY (crypto price data)
+#   SHELLBOOK_API_KEY (Shellbook write tools)
 ENVEOF
   log "Saved config to $ENV_FILE"
 fi
 
 # ── Export all env vars ───────────────────────
+# These mirror the .env defaults — keep in sync.
 export XPR_ACCOUNT XPR_NETWORK XPR_RPC_ENDPOINT
 export ANTHROPIC_API_KEY AGENT_MODEL OPENCLAW_HOOK_TOKEN
 export POLL_ENABLED=true POLL_INTERVAL
+export INDEXER_URL="${INDEXER_URL:-https://indexer.xpragents.com}"
 export XPR_PERMISSION="${XPR_PERMISSION:-active}"
-export AGENT_MAX_TURNS="${AGENT_MAX_TURNS:-10}"
-export MAX_TRANSFER_AMOUNT="${MAX_TRANSFER_AMOUNT:-1000000}"
+export AGENT_MODE="${AGENT_MODE:-worker}"
+export AGENT_MAX_TURNS="${AGENT_MAX_TURNS:-20}"
+export MAX_TRANSFER_AMOUNT="${MAX_TRANSFER_AMOUNT}"
+export AGENT_PUBLIC_URL="${AGENT_PUBLIC_URL:-}"
 export A2A_AUTH_REQUIRED="${A2A_AUTH_REQUIRED:-true}"
 export A2A_TOOL_MODE="${A2A_TOOL_MODE:-full}"
+export A2A_SIGNING_KEY="${A2A_SIGNING_KEY:-}"
+export COST_MARGIN="${COST_MARGIN:-2.0}"
 export TELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN:-}"
 export PINATA_JWT="${PINATA_JWT:-}"
 export PORT="${PORT:-8080}"