#691 - Adopt wayfinder + implement, reshape planning pipeline into spec/plan review

.claude/skills/implement/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: implement
+description: Implement a piece of work based on a spec or set of tickets.
+disable-model-invocation: true
+---
+
+Implement the work described by the user in the spec or ticket(s).
+
+Work one ticket at a time, from a fresh context per ticket. If the ticket isn't on a branch yet, branch from `develop` as `{issue-number}-{kebab-title}` per the repo convention.
+
+Use `/tdd` where possible, at pre-agreed seams.
+
+Run checks as you go, not just at the end:
+
+- **Frontend** (`angular-client/`): typecheck/build regularly; run single Karma specs while iterating (`ng test`), the full suite once at the end; `npx prettier --check` + `npx ng lint` before finishing.
+- **Backend** (`scylla-server/`): `cargo build` and single tests regularly, `cargo test` once at the end.
+
+Once the behaviour is done, use `/code-review` to review the work.
+
+Commit with `/commit` (applies the `#{ticket-number} - {description}` convention) to the ticket's branch. Do not push or open a PR unless asked — that's `/open-pr`.

.claude/skills/to-spec/SKILL.md

@@ -8,15 +8,19 @@ This skill takes the current conversation context and codebase understanding and
 
 Issue tracker conventions live in `docs/agents/issue-tracker.md`; the triage label vocabulary lives in `docs/agents/triage-labels.md`.
 
+A spec is a **review artifact** — it is staged and reviewed as a PR before it publishes as an issue. See `docs/agents/spec-review.md`.
+
 ## Process
 
 1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the spec, and respect any ADRs in the area you're touching.
 
+If a wayfinder map fed this spec, read the map's Decisions-so-far as the source and link the spec back to it. A large effort may be several specs — run this skill once per coherent feature.
+
 2. Sketch out the seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better — the ideal number is one.
 
 Check with the user that these seams match their expectations.
 
-3. Write the spec using the template below, then publish it to the project issue tracker. Apply the `ready-for-agent` triage label - no need for additional triage.
+3. Write the spec using the template below to `docs/spec/<name>/spec.md`, and open it as a PR for review (`docs/agents/spec-review.md`). Once the PR is approved and merged, publish the spec as an issue and apply the `ready-for-agent` triage label - no need for additional triage. `to-tickets` then breaks it into implementation tickets parented to this spec.
 
 <spec-template>
 

.claude/skills/to-tickets/SKILL.md

@@ -10,6 +10,8 @@ Break a plan, spec, or conversation into a set of **tickets** — tracer-bullet
 
 Issue tracker conventions live in `docs/agents/issue-tracker.md`; the triage label vocabulary lives in `docs/agents/triage-labels.md`.
 
+A ticket set is a **review artifact** — it is drafted as files and reviewed as a PR before the tickets publish. This is the gate that keeps unreviewed tickets off the tracker. See `docs/agents/spec-review.md`.
+
 ## Process
 
 ### 1. Gather context
@@ -60,9 +62,13 @@ Ask the user:
 
 Iterate until the user approves the breakdown.
 
-### 5. Publish the tickets to the issue tracker
+### 5. Stage the tickets for review
+
+Draft the approved tickets as local files under `docs/spec/<name>/` — one kebab-named file per ticket, using the issue-body template below — and open them as a PR against `develop` (draft per the repo convention, marked ready when set). This is the review gate (`docs/agents/spec-review.md`): the slicing is reviewed as a diff before any issue exists.
+
+### 6. Publish once the review PR merges
 
-Publish the approved tickets to the project issue tracker (GitHub Issues — see `docs/agents/issue-tracker.md`). Publish one issue per ticket in dependency order (blockers first) so each ticket's blocking edges can reference real issue identifiers. Use GitHub's native sub-issue / blocking relationship where it fits; otherwise set each ticket's "Blocked by" to the blocking issues. Apply the `ready-for-agent` triage label unless instructed otherwise — the tickets are agent-grabbable by construction.
+After the PR is approved and merged, create the tickets on the issue tracker (GitHub Issues — see `docs/agents/issue-tracker.md`), one issue per ticket in dependency order (blockers first) so each ticket's blocking edges can reference real issue identifiers. Use GitHub's native sub-issue / blocking relationship where it fits; otherwise set each ticket's "Blocked by" to the blocking issues. Set each ticket's `Parent` to the spec issue. Apply the `ready-for-agent` triage label unless instructed otherwise — the tickets are agent-grabbable by construction. Then delete the temporary `docs/spec/<name>/` drafts; the tracker issues are the durable home.
 
 Do NOT close or modify any parent issue.
 

.claude/skills/wayfinder/SKILL.md

@@ -0,0 +1,137 @@
+---
+name: wayfinder
+description: Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
+disable-model-invocation: true
+---
+
+A loose idea has arrived — too big for one agent session, and wrapped in fog: the way from here to the **destination** isn't visible yet. Wayfinding is about finding that way, not charging at the destination. This skill charts the way as a **shared map** on the repo's issue tracker, then works its tickets one at a time until the route is clear.
+
+The destination varies per effort, and naming it is the first act of charting — it shapes every ticket. It might be a spec to hand off and iterate on, a decision to lock before planning starts, or a change made in place like a data-structure migration. The map is domain-agnostic — engineering work, course content, whatever fits the shape.
+
+## Plan, don't do
+
+Wayfinder is **planning** by default: each ticket resolves a decision, and the map is done when the way is clear — nothing left to decide before someone goes and does the thing. The pull to just do the work is usually the signal you've reached the edge of the map and it's time to hand off. An effort can override this in its **Notes** — carrying execution into the map itself — but absent that, produce decisions, not deliverables.
+
+## Refer by name
+
+Every map and ticket is an issue, so it has a **name** — its title. In everything the human reads — narration, the map's Decisions-so-far — refer to it by that name, never by a bare id, number, or slug. A wall of `#42, #43, #44` is illegible; names read at a glance. The id and URL don't vanish — a name wraps its link — but they ride *inside* the name, never stand in for it.
+
+## The Map
+
+The map is a single issue on this repo's issue tracker, labelled `wayfinder:map` — the canonical artifact. Its tickets are child issues of the map.
+
+The map is an **index**, not a store. It lists the decisions made and points at the tickets that hold their detail; a decision lives in exactly one place — its ticket — so the map never restates it, only gists it and links.
+
+Argos tracks issues on GitHub. See the **Wayfinding operations** section of `docs/agents/issue-tracker.md` for how the map, its child tickets, blocking, and frontier queries are physically expressed here.
+
+### The map body
+
+The whole map at low resolution, loaded once per session. Open tickets are **not** listed — they are open child issues, found by query.
+
+```markdown
+## Destination
+
+<what reaching the end of this map looks like — the spec, decision, or change this effort is finding its way to. One or two lines; every session orients to it before choosing a ticket.>
+
+## Notes
+
+<domain; skills every session should consult; standing preferences for this effort>
+
+## Decisions so far
+
+<!-- the index — one line per closed ticket: enough to judge relevance, then zoom the link for the detail the ticket holds -->
+
+- [<closed ticket title>](link) — <one-line gist of the answer>
+
+## Not yet specified
+
+<!-- see "Fog of war": in-scope fog you can't ticket yet; graduates as the frontier advances -->
+
+## Out of scope
+
+<!-- see "Out of scope": work ruled beyond the destination; closed, never graduates -->
+```
+
+### Tickets
+
+Each ticket is a **child issue** of the map; the tracker's issue id is its identity. Its body is the question, sized to one 100K token agent session:
+
+```markdown
+## Question
+
+<the decision or investigation this ticket resolves>
+```
+
+Each ticket carries a `wayfinder:<type>` label — one of `research`, `prototype`, `grilling`, `task` (see [Ticket Types](#ticket-types)).
+
+A session **claims** a ticket by assigning it to the dev driving the map, **first**, before any work, so concurrent sessions skip it. That assignee _is_ the claim: an open, unassigned ticket is unclaimed.
+
+Blocking uses the tracker's **native** dependency relationship — essential because it renders the frontier _visually_ in the tracker's own UI, so the human sees what's takeable without opening the map. Only a tracker that lacks native blocking falls back to a body convention. A ticket is **unblocked** when every ticket blocking it is closed; the **frontier** is the open, unblocked, unclaimed children — the edge of the known.
+
+The answer isn't part of the body — it's recorded on resolution (see [Work through the map](#work-through-the-map)). Assets created while resolving a ticket are linked from the issue, not pasted in.
+
+## Ticket Types
+
+Every ticket is either **HITL** — human in the loop, worked *with* a human who speaks for themselves — or **AFK**, driven by the agent alone. A HITL ticket only resolves through that live exchange; the agent never stands in for the human's side of it (a grilling agent that answers its own questions has broken this).
+
+- **Research** (AFK): Reading documentation, third-party APIs, or local resources like knowledge bases via the `/research` skill. Creates a markdown summary as a linked asset. Use when knowledge outside the current working directory is required.
+- **Prototype** (HITL): Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the `/prototype` skill. Links the prototype as an asset. Use when "how should it look" or "how should it behave" is the key question.
+- **Grilling** (HITL): Conversation via the `/grilling` and `/domain-modeling` skills, one question at a time. The default case.
+- **Task** (HITL or AFK): Manual work that must happen before a *decision* can be made — nothing to decide, prototype, or research, but the discussion is blocked until it's done. Signing up for a service so its API can be judged, provisioning access, moving data so its shape can be seen. This is the one type that *does* rather than decides — and it earns its place by unblocking a decision, not by delivering the destination. The agent drives it alone where it can (AFK); otherwise it hands the human a precise checklist (HITL). Resolved when the work is done; the answer records what was done and any resulting facts (credentials location, new URLs, row counts) later tickets depend on.
+
+## Fog of war
+
+The map is _deliberately_ incomplete: don't chart what you can't yet see. Beyond the live tickets lies the **fog of war** — the dim view of decisions and investigations you can tell are coming but can't yet pin down, because they hang on questions still open. Resolving a ticket clears the fog ahead of it, graduating whatever's now specifiable into fresh tickets — one at a time, until the way to the destination is clear and no tickets remain.
+
+The map's **Not yet specified** section is where that dim view is written down: the suspected question, the area to revisit later. It's the undiscovered frontier _toward_ the destination — everything here is in scope, just not sharp enough to ticket. Write as loosely or as fully as the view allows; it doubles as a signpost for collaborators reading where the effort is headed.
+
+**Fog or ticket?** The test is whether you can state the question precisely now — _not_ whether you can answer it now.
+
+- **Ticket when** the question is already sharp — even if it's blocked and you can't act on it yet.
+- **Not yet specified when** you can't yet phrase it that sharply. Don't pre-slice the fog into ticket-sized pieces: it's coarser than a ticket, and one patch may graduate into several tickets, or none, once the frontier reaches it.
+
+**Not yet specified** excludes what's already decided (Decisions so far), what's already a live ticket, and what's out of scope (the next section).
+
+## Out of scope
+
+Fog only ever gathers _toward_ the destination. The destination fixes the scope, so work beyond it is **out of scope** — it isn't fog, and it doesn't belong in **Not yet specified**. It gets its own **Out of scope** section on the map: work you've consciously ruled out of _this_ effort. Scope, not sharpness, lands it here.
+
+Out-of-scope work never graduates — the frontier stops at the destination — so it returns only if the destination is redrawn, and then as a fresh effort, not a resumption.
+
+Ruling something out of scope is a scoping act, not a step on the route. When a ticket that already exists turns out to sit past the destination — mis-scoped in while charting, or exposed by a resolution — **close it** (a closed ticket is unambiguously off the frontier) and leave one line in the **Out of scope** section: the gist plus why it's out of scope, linking the closed ticket. It stays out of **Decisions so far**, which records the route actually walked — a scope boundary isn't a step on it.
+
+## Invocation
+
+Two modes. Either way, **never resolve more than one ticket per session.**
+
+### Chart the map
+
+User invokes with a loose idea.
+
+1. **Name the destination.** Run a `/grilling` and `/domain-modeling` session to pin down what this map is finding its way to — the spec, decision, or change. The destination fixes the scope, so it's settled first.
+2. **Map the frontier.** Grill again, **breadth-first** this time: fan out across the whole space rather than deep on any one thread, surfacing the open decisions and the first steps takeable now. **If this surfaces no fog** — the way to the destination is already clear, the whole journey small enough for one session — you don't need a map. Stop and ask the user how they'd like to proceed.
+3. **Create the map** (label `wayfinder:map`): Destination and Notes filled in, Decisions-so-far empty, the fog sketched into **Not yet specified**.
+4. **Create the tickets you can specify now** as child issues of the map — then wire blocking edges in a **second pass** (issues need ids before they can reference each other). Wiring sorts them into the frontier and the blocked; everything you can't yet specify stays in the fog — the **Not yet specified** section.
+5. Stop — charting the map is one session's work; do not also resolve tickets.
+
+### Work through the map
+
+User invokes with a map (URL or number). A ticket is **optional** — without one, you pick the next decision, not the user.
+
+1. Load the **map** — the low-res view, not every ticket body.
+2. Choose the ticket. If the user named one, use it. Otherwise take the first frontier ticket in order. **Claim it**: assign it to yourself before any work.
+3. Resolve it — **zoom as needed**: fetch the full body of any related or closed ticket on demand; invoke the skills the `## Notes` block names. If in doubt, use `/grilling` and `/domain-modeling`.
+4. Record the resolution: post the answer as a **resolution comment**, **close** the issue, and **append a context pointer** to the map's Decisions-so-far.
+5. Add newly-surfaced tickets (create-then-wire); graduate any fog the answer has made specifiable, clearing each graduated patch from **Not yet specified** so it lives only as its new ticket. If the answer reveals a ticket — this one or another — sits beyond the destination, **rule it out of scope** rather than resolving it on the route. If the decision invalidates other parts of the map, update or delete those tickets.
+
+The user may run unblocked tickets in parallel, so expect other sessions to be editing the tracker concurrently.
+
+## Reaching the destination
+
+The map is done when the frontier is empty and no fog remains — the way to the destination is clear. Wayfinder **hands off** here; it does not build. What happens next depends on the destination:
+
+- **A spec** → run `/to-spec` to synthesise the map's Decisions-so-far into one spec, linked back to the map. A large effort may be **several** specs — run `/to-spec` once per coherent feature, each reading its slice of the map. Each spec then goes through `/to-tickets` → `/implement`.
+- **A locked decision** → the map itself is the artifact; hand it off.
+- **An in-place change** → hand off to `/to-tickets` (or, if it collapsed to a single slice, straight to `/implement`).
+
+Specs and ticket sets produced on the way out are review artifacts — see `docs/agents/spec-review.md`.

CLAUDE.md

@@ -50,7 +50,15 @@ Frontend and backend conventions live alongside their code and auto-load when ed
 
 ## Agent skills
 
-Workflow skills (commit, open-pr, update-pr, address-pr-comments, run-local, verify-telemetry, verify-graph) and Matt Pocock's engineering and issue-authoring skills live in `.claude/skills/`. The AI issue-authoring flow is `grill-with-docs → to-spec → to-tickets → triage`. `grill-with-docs` orchestrates the `grilling` and `domain-modeling` primitives. See `docs/adr/0002-misc-adopt-matt-pocock-skills.md`, `docs/adr/0003-misc-rename-to-spec-to-tickets.md`, and `docs/adr/0004-misc-split-grill-with-docs.md`. The `caveman` terse mode is on by default in this repo as a pilot — see the Communication section above.
+Workflow skills (commit, open-pr, update-pr, address-pr-comments, run-local, verify-telemetry, verify-graph) and Matt Pocock's engineering and issue-authoring skills live in `.claude/skills/`.
+
+The **main flow** (idea → ship): `grill-with-docs` sharpen the idea → `to-spec` write the spec → `to-tickets` slice it into tracer-bullet implementation tickets → `implement` per ticket (drives `tdd`, then `code-review`, then `commit`). A well-understood single feature can skip straight from grill to `to-spec`; a trivial one-liner goes straight to `implement`. `grill-with-docs` orchestrates the `grilling` and `domain-modeling` primitives.
+
+**On-ramps** merge onto that flow: a huge, foggy effort too big for one session → `wayfinder`, which charts a map of investigation tickets on the tracker, then merges at `to-spec` (one map can feed several specs); raw incoming issues → `triage`.
+
+**Spec/plan review:** a spec (`to-spec`) or ticket set (`to-tickets`) is staged as a file and reviewed as a PR before it publishes to the tracker — see `docs/agents/spec-review.md`. Wayfinder investigation tickets are reviewed on the tracker instead and don't pass through this gate.
+
+See `docs/adr/0002-misc-adopt-matt-pocock-skills.md`, `docs/adr/0003-misc-rename-to-spec-to-tickets.md`, `docs/adr/0004-misc-split-grill-with-docs.md`, and `docs/adr/0005-misc-wayfinder-and-spec-review.md`. The `caveman` terse mode is on by default in this repo as a pilot — see the Communication section above.
 
 ### Issue tracker