jonah-fleet 1.0.0

package/templates/prompts/peer-review.md

@@ -0,0 +1,112 @@
+# Peer Review
+
+## Objective
+
+Review a pull request (in Targeted mode for a specific `$PR_NUMBER`, or in Scan mode selecting the highest-priority open PR), evaluate code quality, security, and specification compliance via multi-angle subagent code reviews (`/code-review`), and take exactly one final action: squash-merge if clean, or post findings and bounce the PR back to draft (`gh pr ready <N> --undo`) for in-session author fixes.
+
+## FIRST ACTION — determine the target PR before anything else
+
+Before reading further, before any tool call, and before deciding the mode, check the environment variable `$PR_NUMBER`.
+
+- **$PR_NUMBER is set → Targeted mode.** The value of `$PR_NUMBER` is your target PR. You may also check `$PR_URL`. Skip all selection logic.
+- **$PR_NUMBER is not set → Scan mode.** Only then select a PR by priority.
+
+**Targeted mode is sticky: it can never fall back to Scan mode.** Once the invocation contains a PR reference, you must review exactly that PR. If you cannot act on it (closed/merged/missing), STOP and log FAILURE.
+
+## Definition of Done
+
+The run is SUCCESS only if ALL of these are true:
+
+- [ ] Identified the target PR: if one was named in the invocation, reviewed exactly that PR; otherwise listed open PRs and selected one by priority
+- [ ] Ran the code-review pass (`/code-review` and security pass), and posted findings as inline review comments
+- [ ] Took exactly one final action: squash-merged (if PR is good, CI green and present, linked issue exists) OR posted findings and **converted the PR back to draft** (`gh pr ready <N> --undo`) for author/autowork in-session fixes OR, if round cap reached at round 5 with blocking findings, converted to draft and escalated to human
+- [ ] If merging: captured deferred non-blocking findings per materiality bar (filed follow-up issues for material ones, batched or dropped immaterial ones)
+- [ ] If in Scan mode and no eligible PRs exist, logged SUCCESS with "No PRs to review"
+
+If any criterion cannot be met, stop immediately and log FAILURE with the reason.
+
+## Constraints
+
+- **Max rounds per PR**: 5 — at round 5 the run must terminate in a merge (if no blocking findings remain) or human escalation, never another ordinary bounce.
+- **Max iterations**: 65 — after 65 tool call rounds without completing Definition of Done, STOP. Log FAILURE with category `token_limit`.
+- **Max scope**: one PR per run. Do not review a second PR after finishing the first.
+- **No speculative work**: review only the diff in the PR.
+- **Language Requirement**: All GitHub comments, review notes, and follow-up issues MUST be written in **English**.
+- **Session link footer**: sign every GitHub post with the Antigravity run footer (`_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID})_`).
+
+## Final action: merge or bounce to draft
+
+Every review ends in exactly one of two states:
+- **Merge** — only if PR is good, CI is green and verified on the head commit, and has a linked issue (`Closes #N`).
+  - Sequence: (1) squash-merge, (2) submit held review comments, (3) file follow-up issues for deferred material findings.
+  - Immaterial findings (style/preference) default to dying in the review thread or getting batched.
+  - Mechanical doc fixes (missing changelog line, doc typo in diff) can be committed directly to `main` after squash-merge.
+- **Bounce to draft** — if any **blocking** finding remains (correctness bug, security flaw, failing/missing CI, broken contract):
+  - Submit review as `COMMENT` (never `REQUEST_CHANGES` on same-account PRs).
+  - Convert PR back to draft: `gh pr ready <N> --undo`.
+  - Autowork in-session polling detects the bounce, applies fixes, and re-marks ready.
+
+## Negative examples (DO NOT do these)
+
+- Do not review or list any other PR when `$PR_NUMBER` is set.
+- Do not continue reviewing a PR after discovering it is already merged or closed.
+- Do not merge a PR with failing or absent CI checks.
+- Do not leave a PR in limbo — always merge or convert back to draft.
+- Do not attempt `REQUEST_CHANGES` or `APPROVE` on own PRs (GitHub rejects same-account review states). Always use `COMMENT` + draft toggle.
+- On re-review, do not raise new findings in code that was unchanged since the prior review — only inspect the delta commits.
+- Do not bounce a PR for non-blocking style/preference findings when all correctness checks pass.
+
+## Instructions
+
+### Step 0: Determine the target PR (do this FIRST)
+
+Check if `$PR_NUMBER` is set:
+- **$PR_NUMBER is set → Targeted mode.** Review that exact PR. Skip selection steps 1–2.
+- **$PR_NUMBER is not set → Scan mode.** Proceed to steps 1–2.
+
+### Steps 1–2: Select a PR (Scan mode only)
+
+1. List all open PRs, excluding drafts and pure log PRs (`.github/prompts/logs/**`).
+2. Prioritize:
+   - **Category A (re-review)**: PRs with prior review comments where author has pushed new fix commits.
+   - **Category B (first review)**: Brand new PRs ready for review.
+
+### Step 3: Round tracking & Starting Review marker
+
+- Post a "Starting review (round N)" comment on the target PR to claim the review window.
+- Check round count `N`. If `N >= 5` and blocking findings persist, prepare to escalate.
+
+### Step 4: Multi-Angle Code Review Pass
+
+1. Run `/code-review` over the diff (or delta commits if re-review) evaluating:
+   - **Standards**: Conformance to `AGENTS.md` (or `CLAUDE.md`/`GEMINI.md`), conventions, and architecture.
+   - **Spec Compliance**: Verification against the linked issue's deliverables (`## Tasks`).
+2. Run Security Pass: auth gates, permission checks, injection risks, sensitive credentials.
+3. If PR modifies rendered UI, verify screenshots or visual components if tooling/scripts are available.
+4. Run repository verification commands (tests, type-check) if CI status is unconfirmed.
+
+### Step 5: Classify Findings & Make Decision
+
+Classify each finding:
+- **Blocking**: Broken logic, security hole, data loss, regression, broken tests, missing linked issue.
+- **Non-blocking**: Minor refactor, style preference, performance micro-optimization.
+
+### Step 6: Execute Final Action
+
+- **If Blocking findings exist**:
+  - If `N < 5`: Post inline comments, submit review as `COMMENT`, and convert PR to draft (`gh pr ready <N> --undo`).
+  - If `N >= 5`: Convert PR to draft, post summary comment escalating to repo maintainer, and apply `needs-human` label.
+- **If Clean (or only Non-blocking findings)**:
+  - Squash-merge the PR: `gh pr merge <N> --squash --delete-branch`.
+  - Submit held review comments.
+  - File follow-up issues for material non-blocking findings.
+  - If mechanical doc fixes are needed, commit directly to `main`.
+
+## Logging
+
+After completing (SUCCESS or FAILURE), write a log file to `.github/prompts/logs/peer-review/{timestamp}.md` following the schema in `.github/prompts/logs/_template.md`. Include:
+- Prompt SHA
+- Target PR number and decision (MERGE / BOUNCE / ESCALATE)
+- Execution trace and findings summary
+
+**Important**: Commit the log file directly to `main` and push. Follow the Log delivery fallback in `ORCHESTRATION.md` if direct push fails.

package/templates/prompts/product-planning.md

@@ -0,0 +1,67 @@
+# Product Planning
+
+## Objective
+
+Turn strategy and evidence into **well-scoped, ready-to-build work** and a **current roadmap** — the "plan" between analytics/measurement and autowork's build phase. Each run reads roadmap priorities, analytics signals, and user feedback to **propose** the next units of product work: new feature issues, formal specs/PRDs for larger epics, backlog re-ranking recommendations, and roadmap updates.
+
+This routine runs behind a **human approval gate**: it **never files autowork-ready issues on its own**. It stages proposals in one planning issue for operator approval; only a subsequent operator-approved **Promote** run creates the real issues autowork can claim.
+
+## Definition of Done
+
+This routine runs in two modes: **Propose** (scheduled cron sweep / unapproved fire) and **Promote** (operator-approved fire).
+
+In **Propose mode**, SUCCESS requires:
+- [ ] Read current roadmap, domain documentation, and recent feedback/analytics findings
+- [ ] Created or updated exactly one dated staging issue (`🗺️ Product Plan — {date}`) containing:
+  - Up to 3 well-scoped proposals (Summary/Tasks/Why/Complexity)
+  - Backlog re-ranking recommendations
+  - Formal `/to-spec` PRD drafts for any proposal above `size/M`
+  - Proposed `ROADMAP.md` updates
+- [ ] Filed ZERO autowork-ready issues without approval
+
+In **Promote mode**, SUCCESS requires:
+- [ ] Verified operator approval directives from fire payload
+- [ ] Created real, labeled GitHub issues for approved proposals using `/to-tickets` for epic decomposition
+- [ ] Applied approved backlog re-rankings
+- [ ] Committed approved changes to `ROADMAP.md` if explicitly approved
+- [ ] Annotated the staging issue with created issue numbers (`✅ Created → #N`)
+
+If any criterion cannot be met, stop immediately and log FAILURE with the reason.
+
+## Constraints
+
+- **Max iterations**: 30 — after 30 tool call rounds without completing Definition of Done, STOP. Log FAILURE with category `token_limit`.
+- **Max scope**: planning and staging only. Do not implement code or open feature PRs.
+- **Language Requirement**: All GitHub issue titles, descriptions, task checklists, and comments MUST be written in **English**.
+
+## Instructions
+
+### Mode 0: Determine Propose vs Promote Mode
+
+- **Promote mode**: Payload contains approval tokens (e.g. `Approve #1, #2`, `Approve roadmap`). Proceed to Step 4 (Promote).
+- **Propose mode**: Scheduled sweep or no approval directives. Proceed to Steps 1–3 (Propose).
+
+### Steps 1–3: Propose Mode (Staging Proposals)
+
+1. Read `ROADMAP.md`, `AGENTS.md`, and open issues.
+2. Draft up to 3 high-impact proposals based on roadmap priorities and user feedback.
+3. For proposals sized `size/M` or above, draft a formal specification using `/to-spec`.
+4. Stage all proposals in a dedicated staging issue: `🗺️ Product Plan — {YYYY-MM-DD}` assigned to the repo maintainer.
+
+### Step 4: Promote Mode (Approved Execution)
+
+1. For each approved proposal in the staging issue:
+   - Create a GitHub issue with the full specification and appropriate labels (`type/*`, `size/*`, `priority/*`).
+   - If the proposal is an epic, decompose into child tickets using `/to-tickets`.
+2. Apply approved backlog re-rankings.
+3. If roadmap edits were approved, update `ROADMAP.md` directly on `main`.
+4. Update the staging issue checklist with references to created issues.
+
+## Logging
+
+After completing (SUCCESS or FAILURE), write a log file to `.github/prompts/logs/product-planning/{timestamp}.md` following the schema in `.github/prompts/logs/_template.md`. Include:
+- Prompt SHA
+- Mode (Propose or Promote)
+- Staged or promoted proposals tally
+
+**Important**: Commit the log file directly to `main` and push. Follow the Log delivery fallback in `ORCHESTRATION.md` if direct push fails.

package/templates/skills/code-review/SKILL.md

@@ -0,0 +1,87 @@
+---
+name: code-review
+description: "Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\"."
+---
+
+Two-axis review of the diff between `HEAD` and a fixed point the user supplies:
+
+- **Standards**: does the code conform to this repo's documented coding standards?
+- **Spec**: does the code faithfully implement the originating issue / spec?
+
+Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings.
+
+The issue tracker should have been provided to you. If `docs/agents/issue-tracker.md` is missing, tell the user to run `/setup-matt-pocock-skills`.
+
+## Process
+
+### 1. Pin the fixed point
+
+Whatever the user said is the fixed point (a commit SHA, branch name, tag, `main`, `HEAD~5`, etc.). If they didn't specify one, ask for it.
+
+Capture the diff command once: `git diff <fixed-point>...HEAD` (three-dot, so the comparison is against the merge-base). Also note the list of commits via `git log <fixed-point>..HEAD --oneline`.
+
+Before going further, confirm the fixed point resolves (`git rev-parse <fixed-point>`) and the diff is non-empty. A bad ref or empty diff should fail here, not inside two parallel sub-agents.
+
+### 2. Identify the spec source
+
+Look for the originating spec, in this order:
+
+1. Issue references in the commit messages (`#123`, `Closes #45`, GitLab `!67`, etc.), fetched via the workflow in `docs/agents/issue-tracker.md`.
+2. A path the user passed as an argument.
+3. A spec file under `docs/`, `specs/`, or `.scratch/` matching the branch name or feature.
+4. If nothing is found, ask the user where the spec is. If they say there isn't one, the **Spec** sub-agent will skip and report "no spec available".
+
+### 3. Identify the standards sources
+
+Anything in the repo that documents how code should be written, such as `CODING_STANDARDS.md` or `CONTRIBUTING.md`.
+
+On top of whatever the repo documents, the Standards axis always carries the **smell baseline** below: a fixed set of Fowler code smells (_Refactoring_, ch.3) that applies even when a repo documents nothing. Two rules bind it:
+
+- **The repo overrides.** A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell.
+- **Always a judgement call.** Each smell is a labelled heuristic ("possible Feature Envy"), never a hard violation. Like any standard here, skip anything tooling already enforces.
+
+Each smell reads *what it is* → *how to fix*; match it against the diff:
+
+- **Mysterious Name**: a function, variable, or type whose name doesn't reveal what it does or holds. → rename it; if no honest name comes, the design's murky.
+- **Duplicated Code**: the same logic shape appears in more than one hunk or file in the change. → extract the shared shape, call it from both.
+- **Feature Envy**: a method that reaches into another object's data more than its own. → move the method onto the data it envies.
+- **Data Clumps**: the same few fields or params keep travelling together (a type wanting to be born). → bundle them into one type, pass that.
+- **Primitive Obsession**: a primitive or string standing in for a domain concept that deserves its own type. → give the concept its own small type.
+- **Repeated Switches**: the same `switch`/`if`-cascade on the same type recurs across the change. → replace with polymorphism, or one map both sites share.
+- **Shotgun Surgery**: one logical change forces scattered edits across many files in the diff. → gather what changes together into one module.
+- **Divergent Change**: one file or module is edited for several unrelated reasons. → split so each module changes for one reason.
+- **Speculative Generality**: abstraction, parameters, or hooks added for needs the spec doesn't have. → delete it; inline back until a real need shows.
+- **Message Chains**: long `a.b().c().d()` navigation the caller shouldn't depend on. → hide the walk behind one method on the first object.
+- **Middle Man**: a class or function that mostly just delegates onward. → cut it, call the real target direct.
+- **Refused Bequest**: a subclass or implementer that ignores or overrides most of what it inherits. → drop the inheritance, use composition.
+
+### 4. Spawn both sub-agents in parallel
+
+**Standards sub-agent prompt** should include:
+
+- The full diff command and commit list.
+- The list of standards-source files you found in step 3, **plus the smell baseline from step 3** pasted in full (the sub-agent has no other access to it).
+- The brief: "Report, per file/hunk where relevant, (a) every place the diff violates a documented standard: cite the standard (file + the rule); and (b) any baseline smell you spot: name it and quote the hunk. Distinguish hard violations from judgement calls: documented-standard breaches can be hard, but baseline smells are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words."
+
+**Spec sub-agent prompt** should include:
+
+- The diff command and commit list.
+- The path or fetched contents of the spec.
+- The brief: "Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line for each finding. Under 400 words."
+
+If the spec is missing, skip the Spec sub-agent and note this in the final report.
+
+### 5. Aggregate
+
+Present the two reports under `## Standards` and `## Spec` headings, verbatim or lightly cleaned. Do **not** merge or rerank findings, because the two axes are deliberately separate (see _Why two axes_).
+
+End with a one-line summary: total findings per axis, and the worst issue _within each axis_ (if any). Don't pick a single winner across axes: that's the reranking the separation exists to prevent.
+
+## Why two axes
+
+A change can pass one axis and fail the other:
+
+- Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.**
+- Code that does exactly what the issue asked but breaks the project's conventions → **Spec pass, Standards fail.**
+
+Reporting them separately stops one axis from masking the other.

package/templates/skills/code-review/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Code Review"
+  short_description: "Review a diff on standards and spec"

package/templates/skills/codebase-design/DEEPENING.md

@@ -0,0 +1,37 @@
+# Deepening
+
+How to deepen a cluster of shallow modules safely, given its dependencies. Assumes the vocabulary in [SKILL.md](SKILL.md): **module**, **interface**, **seam**, **adapter**.
+
+## Dependency categories
+
+When assessing a candidate for deepening, classify its dependencies. The category determines how the deepened module is tested across its seam.
+
+### 1. In-process
+
+Pure computation, in-memory state, no I/O. Always deepenable: merge the modules and test through the new interface directly. No adapter needed.
+
+### 2. Local-substitutable
+
+Dependencies that have local test stand-ins (PGLite for Postgres, in-memory filesystem). Deepenable if the stand-in exists. The deepened module is tested with the stand-in running in the test suite. The seam is internal; no port at the module's external interface.
+
+### 3. Remote but owned (Ports & Adapters)
+
+Your own services across a network boundary (microservices, internal APIs). Define a **port** (interface) at the seam. The deep module owns the logic; the transport is injected as an **adapter**. Tests use an in-memory adapter. Production uses an HTTP/gRPC/queue adapter.
+
+Recommendation shape: *"Define a port at the seam, implement an HTTP adapter for production and an in-memory adapter for testing, so the logic sits in one deep module even though it's deployed across a network."*
+
+### 4. True external (Mock)
+
+Third-party services (Stripe, Twilio, etc.) you don't control. The deepened module takes the external dependency as an injected port; tests provide a mock adapter.
+
+## Seam discipline
+
+- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a port unless at least two adapters are justified (typically production + test). A single-adapter seam is just indirection.
+- **Internal seams vs external seams.** A deep module can have internal seams (private to its implementation, used by its own tests) as well as the external seam at its interface. Don't expose internal seams through the interface just because tests use them.
+
+## Testing strategy: replace, don't layer
+
+- Old unit tests on shallow modules become waste once tests at the deepened module's interface exist; delete them.
+- Write new tests at the deepened module's interface. The **interface is the test surface**.
+- Tests assert on observable outcomes through the interface, not internal state.
+- Tests should survive internal refactors, since they describe behaviour, not implementation. If a test has to change when the implementation changes, it's testing past the interface.

package/templates/skills/codebase-design/DESIGN-IT-TWICE.md

@@ -0,0 +1,44 @@
+# Design It Twice
+
+When the user wants to explore alternative interfaces for a chosen deepening candidate, use this parallel sub-agent pattern. Based on "Design It Twice" (Ousterhout): your first idea is unlikely to be the best.
+
+Uses the vocabulary in [SKILL.md](SKILL.md): **module**, **interface**, **seam**, **adapter**, **leverage**.
+
+## Process
+
+### 1. Frame the problem space
+
+Before spawning sub-agents, write a user-facing explanation of the problem space for the chosen candidate:
+
+- The constraints any new interface would need to satisfy
+- The dependencies it would rely on, and which category they fall into (see [DEEPENING.md](DEEPENING.md))
+- A rough illustrative code sketch to ground the constraints, not a proposal, just a way to make the constraints concrete
+
+Show this to the user, then immediately proceed to Step 2. The user reads and thinks while the sub-agents work in parallel.
+
+### 2. Spawn sub-agents
+
+Spawn 3+ sub-agents in parallel. Each must produce a **radically different** interface for the deepened module.
+
+Prompt each sub-agent with a separate technical brief (file paths, coupling details, dependency category from [DEEPENING.md](DEEPENING.md), what sits behind the seam). The brief is independent of the user-facing problem-space explanation in Step 1. Give each agent a different design constraint:
+
+- Agent 1: "Minimize the interface: aim for 1–3 entry points max. Maximise leverage per entry point."
+- Agent 2: "Maximise flexibility: support many use cases and extension."
+- Agent 3: "Optimise for the most common caller: make the default case trivial."
+- Agent 4 (if applicable): "Design around ports & adapters for cross-seam dependencies."
+
+Include both [SKILL.md](SKILL.md) vocabulary and CONTEXT.md vocabulary in the brief so each sub-agent names things consistently with the architecture language and the project's domain language.
+
+Each sub-agent outputs:
+
+1. Interface (types, methods, params, plus invariants, ordering, error modes)
+2. Usage example showing how callers use it
+3. What the implementation hides behind the seam
+4. Dependency strategy and adapters (see [DEEPENING.md](DEEPENING.md))
+5. Trade-offs: where leverage is high, where it's thin
+
+### 3. Present and compare
+
+Present designs sequentially so the user can absorb each one, then compare them in prose. Contrast by **depth** (leverage at the interface), **locality** (where change concentrates), and **seam placement**.
+
+After comparing, give your own recommendation: which design you think is strongest and why. If elements from different designs would combine well, propose a hybrid. Be opinionated: the user wants a strong read, not a menu.

package/templates/skills/codebase-design/SKILL.md

@@ -0,0 +1,114 @@
+---
+name: codebase-design
+description: Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
+---
+
+# Codebase Design
+
+Design **deep modules**: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface. Use this language and these principles wherever code is being designed or restructured. The aim is leverage for callers, locality for maintainers, and testability for everyone.
+
+## Glossary
+
+Use these terms exactly: don't substitute "component," "service," "API," or "boundary." Consistent language is the whole point.
+
+**Module**: anything with an interface and an implementation. Deliberately scale-agnostic: a function, class, package, or tier-spanning slice. _Avoid_: unit, component, service.
+
+**Interface**: everything a caller must know to use the module correctly: the type signature, but also invariants, ordering constraints, error modes, required configuration, and performance characteristics. _Avoid_: API, signature (too narrow, they refer only to the type-level surface).
+
+**Implementation**: what's inside a module, its body of code. Distinct from **Adapter**: a thing can be a small adapter with a large implementation (a Postgres repo) or a large adapter with a small implementation (an in-memory fake). Reach for "adapter" when the seam is the topic; "implementation" otherwise.
+
+**Depth**: leverage at the interface. The amount of behaviour a caller (or test) can exercise per unit of interface they have to learn. A module is **deep** when a large amount of behaviour sits behind a small interface, **shallow** when the interface is nearly as complex as the implementation.
+
+**Seam** _(Michael Feathers)_: a place where you can alter behaviour without editing in that place; the *location* at which a module's interface lives. Where to put the seam is its own design decision, distinct from what goes behind it. _Avoid_: boundary (overloaded with DDD's bounded context).
+
+**Adapter**: a concrete thing that satisfies an interface at a seam. Describes *role* (what slot it fills), not substance (what's inside).
+
+**Leverage**: what callers get from depth. More capability per unit of interface they learn. One implementation pays back across N call sites and M tests.
+
+**Locality**: what maintainers get from depth. Change, bugs, knowledge, and verification concentrate in one place rather than spreading across callers. Fix once, fixed everywhere.
+
+## Deep vs shallow
+
+**Deep module** = small interface + lots of implementation:
+
+```
+┌─────────────────────┐
+│   Small Interface   │  ← Few methods, simple params
+├─────────────────────┤
+│                     │
+│  Deep Implementation│  ← Complex logic hidden
+│                     │
+└─────────────────────┘
+```
+
+**Shallow module** = large interface + little implementation (avoid):
+
+```
+┌─────────────────────────────────┐
+│       Large Interface           │  ← Many methods, complex params
+├─────────────────────────────────┤
+│  Thin Implementation            │  ← Just passes through
+└─────────────────────────────────┘
+```
+
+When designing an interface, ask:
+
+- Can I reduce the number of methods?
+- Can I simplify the parameters?
+- Can I hide more complexity inside?
+
+## Principles
+
+- **Depth is a property of the interface, not the implementation.** A deep module can be internally composed of small, mockable, swappable parts; they just aren't part of the interface. A module can have **internal seams** (private to its implementation, used by its own tests) as well as the **external seam** at its interface.
+- **The deletion test.** Imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
+- **The interface is the test surface.** Callers and tests cross the same seam. If you want to test *past* the interface, the module is probably the wrong shape.
+- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a seam unless something actually varies across it.
+
+## Designing for testability
+
+Good interfaces make testing natural:
+
+1. **Accept dependencies, don't create them.**
+
+   ```typescript
+   // Testable
+   function processOrder(order, paymentGateway) {}
+
+   // Hard to test
+   function processOrder(order) {
+     const gateway = new StripeGateway();
+   }
+   ```
+
+2. **Return results, don't produce side effects.**
+
+   ```typescript
+   // Testable
+   function calculateDiscount(cart): Discount {}
+
+   // Hard to test
+   function applyDiscount(cart): void {
+     cart.total -= discount;
+   }
+   ```
+
+3. **Small surface area.** Fewer methods = fewer tests needed. Fewer params = simpler test setup.
+
+## Relationships
+
+- A **Module** has exactly one **Interface** (the surface it presents to callers and tests).
+- **Depth** is a property of a **Module**, measured against its **Interface**.
+- A **Seam** is where a **Module**'s **Interface** lives.
+- An **Adapter** sits at a **Seam** and satisfies the **Interface**.
+- **Depth** produces **Leverage** for callers and **Locality** for maintainers.
+
+## Rejected framings
+
+- **Depth as ratio of implementation-lines to interface-lines** (Ousterhout): rewards padding the implementation. We use depth-as-leverage instead.
+- **"Interface" as the TypeScript `interface` keyword or a class's public methods**: too narrow: interface here includes every fact a caller must know.
+- **"Boundary"**: overloaded with DDD's bounded context. Say **seam** or **interface**.
+
+## Going deeper
+
+- **Deepening a cluster given its dependencies**, see [DEEPENING.md](DEEPENING.md): dependency categories, seam discipline, and replace-don't-layer testing.
+- **Exploring alternative interfaces**, see [DESIGN-IT-TWICE.md](DESIGN-IT-TWICE.md): spin up parallel sub-agents to design the interface several radically different ways, then compare on depth, locality, and seam placement.

package/templates/skills/codebase-design/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Codebase Design"
+  short_description: "Vocabulary for deep-module design"

package/templates/skills/diagnosing-bugs/SKILL.md

@@ -0,0 +1,138 @@
+---
+name: diagnosing-bugs
+description: Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
+---
+
+# Diagnosing Bugs
+
+A discipline for hard bugs. Skip phases only when explicitly justified.
+
+When exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
+
+## Redact
+
+This skill has you show commands, outputs and captured artifacts. **Redact every secret first**: write `<REDACTED>` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.
+
+If the redacted output is not enough to diagnose the bug, say so and ask the user.
+
+## Phase 1: Build a feedback loop
+
+**This is the skill.** Everything else is mechanical. If you have a **tight** pass/fail signal for the bug (one that goes red on _this_ bug), you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.
+
+Spend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.**
+
+### Ways to construct one, in roughly this order
+
+1. **Failing test** at whatever seam reaches the bug: unit, integration, e2e.
+2. **Curl / HTTP script** against a running dev server.
+3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot.
+4. **Headless browser script** (Playwright / Puppeteer) that drives the UI and asserts on DOM/console/network.
+5. **Replay a captured trace.** Save a real network request / payload / event log to disk; replay it through the code path in isolation.
+6. **Throwaway harness.** Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
+7. **Property / fuzz loop.** If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
+8. **Bisection harness.** If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can `git bisect run` it.
+9. **Differential loop.** Run the same input through old-version vs new-version (or two configs) and diff outputs.
+10. **HITL bash script.** Last resort. If a human must click, drive _them_ with `scripts/hitl-loop.template.sh` so the loop is still structured. Captured output feeds back to you.
+
+Build the right feedback loop, and the bug is 90% fixed.
+
+### Tighten the loop
+
+Treat the loop as a product. Once you have _a_ loop, **tighten** it:
+
+- Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)
+- Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".)
+- Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)
+
+A 30-second flaky loop is barely better than no loop; a 2-second deterministic one is tight, a debugging superpower.
+
+### Non-deterministic bugs
+
+The goal is not a clean repro but a **higher reproduction rate**. Loop the trigger 100×, parallelise, add stress, narrow timing windows, inject sleeps. A 50%-flake bug is debuggable; 1% is not, so keep raising the rate until it's debuggable.
+
+### When you genuinely cannot build a loop
+
+Stop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a redacted captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do **not** proceed to hypothesise without a loop.
+
+### Completion criterion: a tight loop that goes red
+
+Phase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** (a script path, a test invocation, a curl) that you have **already run at least once** (show the invocation and its output, redacted), and that is:
+
+- [ ] **Red-capable**: it drives the actual bug code path and asserts the **user's exact symptom**, so it can go red on this bug and green once fixed. Not "runs without erroring"; it must be able to _catch this specific bug_.
+- [ ] **Deterministic**: same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).
+- [ ] **Fast**: seconds, not minutes.
+- [ ] **Agent-runnable**: you can run it unattended; a human in the loop only via `scripts/hitl-loop.template.sh`.
+
+If you catch yourself reading code to build a theory before this command exists, **stop: jumping straight to a hypothesis is the exact failure this skill prevents.** No red-capable command, no Phase 2.
+
+## Phase 2: Reproduce + minimise
+
+Run the loop. Watch it go red as the bug appears.
+
+Confirm:
+
+- [ ] The loop produces the failure mode the **user** described, not a different failure that happens to be nearby. Wrong bug = wrong fix.
+- [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against).
+- [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it.
+
+### Minimise
+
+Once it's red, shrink the repro to the **smallest scenario that still goes red**. Cut inputs, callers, config, data, and steps **one at a time**, re-running the loop after each cut, and keep only what's load-bearing for the failure.
+
+Why bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts left to suspect) and becomes the clean regression test in Phase 5.
+
+Done when **every remaining element is load-bearing**: removing any one of them makes the loop go green.
+
+Do not proceed until you have reproduced **and** minimised.
+
+## Phase 3: Hypothesise
+
+Generate **3–5 ranked hypotheses** before testing any of them. Single-hypothesis generation anchors on the first plausible idea.
+
+Each hypothesis must be **falsifiable**: state the prediction it makes.
+
+> Format: "If <X> is the cause, then <changing Y> will make the bug disappear / <changing Z> will make it worse."
+
+If you cannot state the prediction, the hypothesis is a vibe: discard or sharpen it.
+
+**Show the ranked list to the user before testing.** They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it; proceed with your ranking if the user is AFK.
+
+## Phase 4: Instrument
+
+Each probe must map to a specific prediction from Phase 3. **Change one variable at a time.**
+
+Tool preference:
+
+1. **Debugger / REPL inspection** if the env supports it. One breakpoint beats ten logs.
+2. **Targeted logs** at the boundaries that distinguish hypotheses.
+3. Never "log everything and grep".
+
+**Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.
+
+**Perf branch.** For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, `performance.now()`, profiler, query plan), then bisect. Measure first, fix second.
+
+## Phase 5: Fix + regression test
+
+Write the regression test **before the fix**, but only if there is a **correct seam** for it.
+
+A correct seam is one where the test exercises the **real bug pattern** as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.
+
+**If no correct seam exists, that itself is the finding.** Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.
+
+If a correct seam exists:
+
+1. Turn the minimised repro into a failing test at that seam.
+2. Watch it fail.
+3. Apply the fix.
+4. Watch it pass.
+5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.
+
+## Phase 6: Cleanup
+
+Required before declaring done:
+
+- [ ] Original repro no longer reproduces (re-run the Phase 1 loop)
+- [ ] Regression test passes (or absence of seam is documented)
+- [ ] All `[DEBUG-...]` instrumentation removed (`grep` the prefix)
+- [ ] Throwaway prototypes deleted (or moved to a clearly-marked debug location)
+- [ ] The hypothesis that turned out correct is stated in the commit / PR message, so the next debugger learns

package/templates/skills/diagnosing-bugs/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Diagnosing Bugs"
+  short_description: "Diagnose hard bugs and regressions"