Skip to content

intent-check: request standard effort/profile instead of frontier/maximum #114

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
sumitake wants to merge 1 commit into from
Closed

intent-check: request standard effort/profile instead of frontier/maximum #114

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions changelog.d/2026-08-18-intent-check-effort-standard.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
### agent-collab — 2026-08-18

#### Changed
- `intent-check` skill now requests `quality_profile: standard` / `effort_class: standard` (was `frontier` / `maximum`). The Step-0 intent check is a bounded two-document interpretation comparison, not architecture-grade deliberation; the top-tier pin made it the most expensive high-frequency managed call in the system with no quality justification. For the `context.documents.intent` route the `quality_profile` knob is functionally inert (identical candidate lists across all profiles), so this is a pure cost reduction with no routing change. Matches the existing `teamwork` / `orchestrate` standard/standard default pattern. Companion workspace PR downgrades the route-level `effort_class` floor so the new request is admitted (workspace merges first — a request below the floor is rejected `effort_ineligible`).
6 changes: 3 additions & 3 deletions plugins/agent-collab/skills/intent-check/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,8 @@
name: intent-check
version: 6.0.5
defaults:
quality_profile: frontier
effort_class: maximum
quality_profile: standard
effort_class: standard

description: Verify that the active primary's interpretation matches the operator's request before consequential planning or execution. Use when the user says "intent check," "confirm what I asked," "check for scope drift," or "/agent-collab:intent-check." Also offer this proactively when a major request has multiple constraints whose omission would materially change the result.
---
Expand All @@ -24,7 +24,7 @@ request. The runtime selects an eligible independent route; the caller does not
construct an agent/action pair.

```json coordinator-request
{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"frontier","effort_class":"maximum","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":"<verbatim operator request>"},{"label":"primary_interpretation","content":"<plain-language interpretation>"}]}
{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"standard","effort_class":"standard","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":"<verbatim operator request>"},{"label":"primary_interpretation","content":"<plain-language interpretation>"}]}
```

## Workflow
Expand Down
2 changes: 1 addition & 1 deletion scripts/skill-build-config.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@
"visual_review_defaults_block": "defaults:\n quality_profile: frontier\n effort_class: maximum\n",
"visual_review_call_params": "with no managed image route in this release",
"orchestrate_defaults_block": "defaults:\n quality_profile: standard\n effort_class: standard\n",
"intent_check_defaults_block": "defaults:\n quality_profile: frontier\n effort_class: maximum\n",
"intent_check_defaults_block": "defaults:\n quality_profile: standard\n effort_class: standard\n",
"teamwork_defaults_block": "defaults:\n quality_profile: standard\n effort_class: standard\n",
"consultant_agent": "an eligible managed consultant"
}
Expand Down
2 changes: 1 addition & 1 deletion skill-specs/intent-check.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ request. The runtime selects an eligible independent route; the caller does not
construct an agent/action pair.

```json coordinator-request
{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"frontier","effort_class":"maximum","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":"<verbatim operator request>"},{"label":"primary_interpretation","content":"<plain-language interpretation>"}]}
{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"standard","effort_class":"standard","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":"<verbatim operator request>"},{"label":"primary_interpretation","content":"<plain-language interpretation>"}]}

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 18, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Ship a runtime that admits the standard-effort request

With the currently packaged 6.0.5/runtime-4.0.4 bundle, this request is below the existing context.documents.intent maximum-effort floor and is therefore rejected as effort_ineligible, so every invocation of intent-check from this tree fails before inference. Merging the companion workspace policy first does not update the standalone runtime bytes selected beneath this plugin root; this change must remain paired with importing the rebuilt, signed bundle that contains the lowered floor (or retain maximum until that bundle is packaged).

AGENTS.md reference: AGENTS.md:L13-L16

Useful? React with 👍 / 👎.

@sumitake sumitake Aug 18, 2026

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Confirmed correct — verified the plugin bundle is a signed native runtime (runtime-manifest.json lists compiled .so artifacts with sha256 + Developer-ID signatures), so the routing floor is baked into signed bytes that the workspace policy change does not update. Merging this skill change against the current 6.0.5/4.0.4 bundle would reject the standard request as effort_ineligible before inference.

Action: holding this PR (back to draft). Per your option (a), the skill-request lowering must ship paired with the rebuilt/re-signed runtime bundle that carries the lowered intent floor — i.e. it belongs in the in-flight v6.0.6 release, not a standalone merge. The workspace source that feeds that rebuild is landing first (agent-collab-workspace#2771, the verify-intent carve-out). Good catch — this prevented a break-before-inference regression.

🤖 Addressed by Claude Code

```

## Workflow
Expand Down
4 changes: 2 additions & 2 deletions tests/test_unified_skill_runtime_contract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,8 +119,8 @@ def test_intent_check_uses_the_descriptor_owned_untargeted_action(self) -> None:
request = json.loads(matches[0])
self.assertEqual(request["logical_action"], "context.documents.intent")
self.assertIsNone(request["target_agent"])
self.assertEqual(request["quality_profile"], "frontier")
self.assertEqual(request["effort_class"], "maximum")
self.assertEqual(request["quality_profile"], "standard")
self.assertEqual(request["effort_class"], "standard")
self.assertEqual(
set(request),
{
Expand Down
Loading