ca-feature
Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.
Install
npx skills add https://github.com/arbiterForge/codeArbiter/tree/main/plugins/ca-pi/skills/ca-feature
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install arbiterforge-codearbiter@llmmart
git clone https://github.com/arbiterForge/codeArbiter.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole arbiterforge/codearbiter collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
/ca-feature — spec-driven feature
The single permitted entry to implementation work. No feature code is written before a spec is approved and tdd Phase 1 clears. A one-line idea is not a spec — brainstorming makes it one.
Typed-artifact pilot boundary
For an existing .html spec/plan match, or when the user explicitly requests
the typed-HTML pilot, load <plugin-root>/includes/artifacts.md before resume
classification or artifact I/O. Its validated identity, authority, binding and
task-state operations replace this command's .md, approval-label and status-cell
assumptions for that pipeline only. A missing or invalid helper is a STOP; never
fall back to interpreting the HTML as Markdown or as an empty artifact. HTML
--farm dispatch is blocked. Legacy Markdown remains the default until the
native-host, consumer and release qualification gates are complete.
Orientation: if .codearbiter/code-map.md is present, read it first — a coarse concern→path→role map that orients task authoring. Absent is fine; it is read-on-demand, populated by context-creation or commit-gate heal.
Resume — an interrupted pipeline is re-entered, never restarted
Before triage, scan <project-root>/.codearbiter/specs/ and plans/ for an existing slug
matching $ARGUMENTS (invoked bare, list every resumable pipeline and ask which). A crash,
compaction, or closed session mid-pipeline loses nothing — the spec, the plan, and each task's
state are on disk. For HTML, obtain state only through the typed-artifact protocol;
do not scrape rendered labels or the embedded JSON directly. On a match, confirm the resume with the user in one line
("resume <slug> at
- Plan exists with non-
ACCEPTEDtasks →executing-plans(its Phase 1 batches only the remaining tasks). - Plan exists, every task
ACCEPTED→commit-gate(the work is done and verified; it was the commit that never happened). - Spec approved, no plan →
writing-plans(<plugin-root>/routines/writing-plans/SKILL.md). - Spec exists but never approved →
brainstorming(<plugin-root>/routines/brainstorming/SKILL.md), at its approval gate — not from scratch.
Re-running brainstorming against an already-approved spec is the failure mode this section exists
to prevent: it discards approved decisions and re-asks answered questions. Only an explicit user
request ("start over") restarts an existing slug — and that is logged to triage.log like any
classification.
Step 0 — change-class triage (logged)
Before routing, classify the request. The small lane applies only when ALL of these hold —
judged against $ARGUMENTS and a quick look at the code, never assumed:
- the change touches ≤ 2 implementation files (plus their tests);
- no §4 reference-map scope-touch: auth/crypto/secrets, dependencies, migrations/schema, telemetry, public API surface, domain vocabulary;
- no new dependency, endpoint, command, or configuration surface;
- the behavior change is expressible as 1–3 concrete, individually testable acceptance criteria.
Small lane: state the mini-spec inline (the 1–3 criteria) and STOP for the user's one-reply
confirmation. On confirmation, append one line to <project-root>/.codearbiter/triage.log
(append-only, >>):
[ISO-8601 timestamp] | BY: <git user.email> | LANE: small | SCOPE: <one-line> | BASIS: <criteria met>
Then route directly to tdd (<plugin-root>/routines/tdd/SKILL.md) — the confirmed criteria are its Phase 1 obligations; Phases 2–6 run
unchanged — and exit through the full commit-gate and finishing-a-development-branch exactly as
the full lane does. The lane trims ceremony, never gates.
Any criterion violated, or uncertain → full lane (below). Uncertainty is full-lane; the triage never guesses.
Flow — full lane
Route through the pipeline in order; each step gates the next:
brainstorming(<plugin-root>/routines/brainstorming/SKILL.md) — refine$ARGUMENTSinto a concrete spec by Socratic questioning: challenge vague language, surface hidden complexity, force trade-offs. Writes the spec to<project-root>/.codearbiter/specs/<slug>.md. Hard gate: no plan and no code until the user approves the spec. Genuinely-unresolved unknowns become[CONFIRM-NN]inopen-questions.md, never guesses.writing-plans(<plugin-root>/routines/writing-plans/SKILL.md) — decompose the approved spec into small tasks, each with an exact path and a verification that maps to atddobligation (it does not replace one). Writes<project-root>/.codearbiter/plans/<slug>.mdwith bijective criterion↔task coverage.executing-plans(<plugin-root>/routines/executing-plans/SKILL.md) — coordinates the plan in small batches with human checkpoints. Each batch is delegated tosubagent-driven-development(<plugin-root>/routines/subagent-driven-development/SKILL.md— fresh author agent per task, spec-compliance review, quality review, fresh verification). The user acknowledges between batches; nothing advances until they do.commit-gate— the only path to a commit; nine gates, including behavioral proof.finishing-a-development-branch— terminal step: open-PR / merge-via-PR / discard. Every change lands through a PR; never a direct write to the default branch.
The autonomous counterpart (/ca-sprint) runs the same spec→plan but passes the full plan to
subagent-driven-development directly, without per-batch checkpoints. That path is its own entry,
not /feature.
Scope routing
Scope determines which author agent subagent-driven-development dispatches per task:
backend-author, frontend-author, or infra-author — per the mapping in tech-stack.md. A
multi-area feature runs the appropriate agent per task. Each transition requires the affected local
tests from <plugin-root>/includes/verification-boundary.md to be green; exhaustive cross-area and
cross-platform proof runs in exact-head hosted CI before merge.
When NOT to use
- A known defect with a reproduction →
/fix. - A behavior-preserving restructure →
/refactor. - A question or quick discussion →
/btw. - Persisting work already written →
/commit.
Hard gate
MUST NOT write feature code before a spec is approved AND tdd Phase 1 clears — the brainstormed
spec in the full lane, the user-confirmed mini-spec in the small lane. MUST NOT take the small lane
unless every Step 0 criterion holds, and MUST log the classification to
.codearbiter/triage.log before tdd begins. MUST NOT skip writing-plans in the full lane.
MUST NOT resolve a [CONFIRM-NN] in the spec by guessing — surface it.
MUST NOT restart an interrupted pipeline whose artifacts exist on disk — resume at the furthest
checkpoint per the Resume ladder, unless the user explicitly asks to start over.
Files (codearbiter)
-
SKILL.md 7.1 KB
--- name: ca-feature description: "Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation." argument-hint: "<what you want to build>" --- # /ca-feature — spec-driven feature The single permitted entry to implementation work. No feature code is written before a spec is approved and `tdd` Phase 1 clears. A one-line idea is not a spec — `brainstorming` makes it one. ## Typed-artifact pilot boundary For an existing `.html` spec/plan match, or when the user explicitly requests the typed-HTML pilot, load `<plugin-root>/includes/artifacts.md` before resume classification or artifact I/O. Its validated identity, authority, binding and task-state operations replace this command's `.md`, approval-label and status-cell assumptions for that pipeline only. A missing or invalid helper is a STOP; never fall back to interpreting the HTML as Markdown or as an empty artifact. HTML `--farm` dispatch is blocked. Legacy Markdown remains the default until the native-host, consumer and release qualification gates are complete. **Orientation:** if `.codearbiter/code-map.md` is present, read it first — a coarse concern→path→role map that orients task authoring. Absent is fine; it is read-on-demand, populated by context-creation or commit-gate heal. ## Resume — an interrupted pipeline is re-entered, never restarted Before triage, scan `<project-root>/.codearbiter/specs/` and `plans/` for an existing slug matching `$ARGUMENTS` (invoked bare, list every resumable pipeline and ask which). A crash, compaction, or closed session mid-pipeline loses nothing — the spec, the plan, and each task's state are on disk. For HTML, obtain state only through the typed-artifact protocol; do not scrape rendered labels or the embedded JSON directly. On a match, confirm the resume with the user in one line ("resume `<slug>` at <point>?") and re-enter at the furthest checkpoint reached: 1. **Plan exists with non-`ACCEPTED` tasks** → `executing-plans` (its Phase 1 batches only the remaining tasks). 2. **Plan exists, every task `ACCEPTED`** → `commit-gate` (the work is done and verified; it was the commit that never happened). 3. **Spec approved, no plan** → `writing-plans` (`<plugin-root>/routines/writing-plans/SKILL.md`). 4. **Spec exists but never approved** → `brainstorming` (`<plugin-root>/routines/brainstorming/SKILL.md`), at its approval gate — not from scratch. Re-running `brainstorming` against an already-approved spec is the failure mode this section exists to prevent: it discards approved decisions and re-asks answered questions. Only an explicit user request ("start over") restarts an existing slug — and that is logged to `triage.log` like any classification. ## Step 0 — change-class triage (logged) Before routing, classify the request. The **small lane** applies only when ALL of these hold — judged against `$ARGUMENTS` and a quick look at the code, never assumed: - the change touches ≤ 2 implementation files (plus their tests); - no §4 reference-map scope-touch: auth/crypto/secrets, dependencies, migrations/schema, telemetry, public API surface, domain vocabulary; - no new dependency, endpoint, command, or configuration surface; - the behavior change is expressible as 1–3 concrete, individually testable acceptance criteria. **Small lane:** state the mini-spec inline (the 1–3 criteria) and STOP for the user's one-reply confirmation. On confirmation, append one line to `<project-root>/.codearbiter/triage.log` (append-only, `>>`): ``` [ISO-8601 timestamp] | BY: <git user.email> | LANE: small | SCOPE: <one-line> | BASIS: <criteria met> ``` Then route directly to `tdd` (`<plugin-root>/routines/tdd/SKILL.md`) — the confirmed criteria are its Phase 1 obligations; Phases 2–6 run unchanged — and exit through the full `commit-gate` and `finishing-a-development-branch` exactly as the full lane does. The lane trims ceremony, never gates. Any criterion violated, or uncertain → **full lane** (below). Uncertainty is full-lane; the triage never guesses. ## Flow — full lane Route through the pipeline in order; each step gates the next: 1. **`brainstorming`** (`<plugin-root>/routines/brainstorming/SKILL.md`) — refine `$ARGUMENTS` into a concrete spec by Socratic questioning: challenge vague language, surface hidden complexity, force trade-offs. Writes the spec to `<project-root>/.codearbiter/specs/<slug>.md`. **Hard gate: no plan and no code until the user approves the spec.** Genuinely-unresolved unknowns become `[CONFIRM-NN]` in `open-questions.md`, never guesses. 2. **`writing-plans`** (`<plugin-root>/routines/writing-plans/SKILL.md`) — decompose the approved spec into small tasks, each with an exact path and a verification that maps to a `tdd` obligation (it does not replace one). Writes `<project-root>/.codearbiter/plans/<slug>.md` with bijective criterion↔task coverage. 3. **`executing-plans`** (`<plugin-root>/routines/executing-plans/SKILL.md`) — coordinates the plan in small batches with human checkpoints. Each batch is delegated to `subagent-driven-development` (`<plugin-root>/routines/subagent-driven-development/SKILL.md` — fresh author agent per task, spec-compliance review, quality review, fresh verification). The user acknowledges between batches; nothing advances until they do. 4. **`commit-gate`** — the only path to a commit; nine gates, including behavioral proof. 5. **`finishing-a-development-branch`** — terminal step: open-PR / merge-via-PR / discard. Every change lands through a PR; never a direct write to the default branch. The autonomous counterpart (`/ca-sprint`) runs the same spec→plan but passes the full plan to `subagent-driven-development` directly, without per-batch checkpoints. That path is its own entry, not `/feature`. ## Scope routing Scope determines which author agent `subagent-driven-development` dispatches per task: `backend-author`, `frontend-author`, or `infra-author` — per the mapping in `tech-stack.md`. A multi-area feature runs the appropriate agent per task. Each transition requires the affected local tests from `<plugin-root>/includes/verification-boundary.md` to be green; exhaustive cross-area and cross-platform proof runs in exact-head hosted CI before merge. ## When NOT to use - A known defect with a reproduction → `/fix`. - A behavior-preserving restructure → `/refactor`. - A question or quick discussion → `/btw`. - Persisting work already written → `/commit`. ## Hard gate MUST NOT write feature code before a spec is approved AND `tdd` Phase 1 clears — the brainstormed spec in the full lane, the user-confirmed mini-spec in the small lane. MUST NOT take the small lane unless every Step 0 criterion holds, and MUST log the classification to `.codearbiter/triage.log` before `tdd` begins. MUST NOT skip `writing-plans` in the full lane. MUST NOT resolve a `[CONFIRM-NN]` in the spec by guessing — surface it. MUST NOT restart an interrupted pipeline whose artifacts exist on disk — resume at the furthest checkpoint per the Resume ladder, unless the user explicitly asks to start over.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.