Agent skill

Ca Feature

by arbiterForge in arbiterForge/codeArbiter

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline.

AGPL-3.0Auto-check passedTesting & QA

Install Ca Feature

skills CLI
$ npx skills add arbiterForge/codeArbiter --skill ca-feature -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install arbiterForge/codeArbiter ca-feature --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/arbiterForge/codeArbiter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ca-pi/skills/ca-feature .claude/skills/ca-feature && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ca-feature
GitHub stars
147
Token cost
~2.2k tokens
SKILL.md length
1,118 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline.

  • Works in 4 steps: Plan exists with non-ACCEPTED tasks →… → Plan exists, every task ACCEPTED →… → Spec approved, no plan → writing-plans… → …
  • Tasks that involve Test-driven development
  • SKILL.md covers Structured-artifact boundary, Resume — an interrupted…, Step 0 — change-class triage… and Flow — full lane, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ca Feature is an agent skill from arbiterForge/codeArbiter. Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Test-driven development and Brainstorming. The repository describes itself as: Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Test-driven development
  • Tasks that involve Brainstorming

Example prompts

  • “/ca-feature”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Plan exists with non-ACCEPTED tasks → executing-plans (its Phase 1 batches only the
  2. Plan exists, every task ACCEPTED → commit-gate (the work is done and verified; it was the
  3. Spec approved, no plan → writing-plans (/routines/writing-plans/SKILL.md).
  4. Spec exists but never approved → brainstorming (/routines/brainstorming/SKILL.md), at its approval gate — not from scratch.

What it can do on your machine

Read from SKILL.md and the folder at commit cd5b0a0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ca Feature loads about 2.2k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 1,118 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from arbiterForge/codeArbiter at commit cd5b0a0, republished under its AGPL-3.0 licence (© arbiterForge). 1,118 words, ~2,210 tokens.

Download SKILL.mdSave it as .claude/skills/ca-feature/SKILL.md (or your agent's skills folder).
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.

Structured-artifact boundary

For new full-lane work or an existing .html spec/plan match, load <plugin-root>/includes/artifacts.md before resume classification or artifact I/O. After lane classification, call _select_authoring_route with the trusted project root, slug, workflow: feature, and the selected lane. Use only its returned mode, format, and paths. For a selected HTML route it checks the installed capability before writing; a missing or invalid helper is a STOP and the workflow must not fall back to Markdown. Its validated identity, authority, binding and task-state operations replace this command's .md, approval-label and status-cell assumptions for that pipeline. New full-lane specs use the installed structured-artifact engine and default to canonical .html. An existing .md pair remains on the legacy path. Discovery requires a complete same-extension spec/plan pair: select that exact pair as authoritative. A mixed-extension or duplicate match is a STOP. A lone spec resumes in its exact format, and the next plan must use the same extension. The workflow must not create, rename, or convert its counterpart to repair ambiguity. HTML --farm dispatch stays blocked. Small-lane behavior is unchanged: its confirmed mini-spec remains inline and does not create a spec artifact.

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. At each actual author or independent reviewer dispatch, use the private _artifactpromptlib.compose_feature_actor_input contract described in tdd and subagent-driven-development; send its returned input to the fresh actor before mutation, execution of discovered commands, or a substantive review verdict. A coordinator's read alone is not delivery.

Resume — an interrupted pipeline is re-entered, never restarted

Before triage, scan <project-root>/.codearbiter/specs/ and plans/ for artifacts whose slug matches $ARGUMENTS (invoked bare, list every resumable pipeline and ask which). Call the private bridge resolver _resolve_workflow_pair with the trusted project root and selected slug; its returned paths and format own this resume. Select a complete same-extension pair as authoritative. A lone spec resumes in its exact format, and the next plan must use the same extension. A mixed-extension or duplicate match is a STOP. A crash, compaction, or closed session mid-pipeline loses nothing — the spec, the plan, and each task's state are on disk. For an HTML pair, obtain state only through the installed engine identity, index, and symbol-scoped read operations; do not scrape rendered labels or embedded JSON. For a Markdown pair, use the existing Markdown status ledger. Resume either exact format without creating or consulting a shadow artifact; the workflow must not create, rename, or convert its counterpart. 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.

Show full SKILL.md (390 more words)Show less

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 route-selected spec path. New full-lane work writes <project-root>/.codearbiter/specs/<slug>.html through the installed engine. 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 matching route-selected plan path 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.

© arbiterForge, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/ca-pi/skills/ca-feature of arbiterForge/codeArbiter.

Open the folder on GitHubat commit cd5b0a0

Compare with similar skills

Ca Feature next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ca Feature compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ca Feature this skillarbiterForge/codeArbiter147—~2.2kAutomated safety check: PassAGPL-3.0
Superpowers Feature WorkflowSYZ-Coder/superpowers-openspec-team-skills196—~891Automated safety check: PassMIT
Evanflow Goevanklem/evanflow418—~2.3kAutomated safety check: PassCustom licence
Component Design With TdadHabitat-Thinking/ai-literacy-superpowers114—~3.3kAutomated safety check: PassCustom licence
Work Issuejoesaby/astro-mermaid123—~891Automated safety check: PassMIT
Context Modes0xNyk/lacp305—~313Automated safety check: PassMIT

Similar skills

  • Superpowers Feature Workflow

    SYZ-Coder/superpowers-openspec-team-skills

    A skill your agent uses when feature work needs the Superpowers stages before or during implementation: brainstorming, design confirmation, implementation planning, worktree setup, test-driven…

    196 GitHub stars~891 tokensUpdated 3 mo ago
    Testing & QAAuto-check passed
  • Evanflow Go

    evanklem/evanflow

    Single entry-point orchestrator for the entire EvanFlow loop.

    418 GitHub stars~2.3k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed
  • Component Design With Tdad

    Habitat-Thinking/ai-literacy-superpowers

    A skill your agent uses when designing a new plugin component (skill, agent, command, or backing script) for the ai-literacy-superpowers plugin or a sister plugin in this marketplace.

    114 GitHub stars~3.3k tokensUpdated 16 days ago
    Testing & QAAuto-check passed
  • Work Issue

    joesaby/astro-mermaid

    End-to-end workflow for resolving a GitHub issue in astro-mermaid — triages complexity, then runs brainstorm → TDD → implement → docs/spec → code review at the right depth.

    123 GitHub stars~891 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Context Modes

    0xNyk/lacp

    Structured work modes for agent sessions. An agent skill from 0xNyk/lacp.

    305 GitHub stars~313 tokensUpdated 15 days ago
    Agent WorkflowsAuto-check passed
  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 54 repos~2.6k tokens
    Agent WorkflowsAuto-check passed

More from arbiterForge/codeArbiter

All 12 skills in this repo
  • Sandbox Claude Inside

    arbiterForge/codeArbiter

    Run Claude Code INSIDE a ca-sandbox box (--with-claude). An agent skill from arbiterForge/codeArbiter.

    147 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Ca Adr

    arbiterForge/codeArbiter

    Record user-decided ADRs or inspect their health read-only. An agent skill from arbiterForge/codeArbiter.

    147 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • Ca Conflict

    arbiterForge/codeArbiter

    Stop everything and surface a rule conflict — persona vs. An agent skill from arbiterForge/codeArbiter.

    147 GitHub stars~574 tokensUpdated yesterday
    Auto-check passed
  • Ca Init

    arbiterForge/codeArbiter

    Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

    147 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Ca Metrics

    arbiterForge/codeArbiter

    Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs.

    147 GitHub stars~966 tokensUpdated yesterday
    Auto-check passed
  • Ca Override

    arbiterForge/codeArbiter

    Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

    147 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

Questions about Ca Feature

What does Ca Feature do?

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. Ca Feature is an agent skill from arbiterForge/codeArbiter. Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline.

When should I use Ca Feature?

Ca Feature fits situations like: tasks that involve Test-driven development; tasks that involve Brainstorming.

How do I install Ca Feature in Claude Code?

Run `npx skills add arbiterForge/codeArbiter --skill ca-feature -a claude-code`. Or copy the skill folder (plugins/ca-pi/skills/ca-feature in arbiterForge/codeArbiter) into .claude/skills/ca-feature in your project. Claude Code loads it when a task matches its description.

How do I install Ca Feature in Codex?

Run `npx skills add arbiterForge/codeArbiter --skill ca-feature -a codex`. Or copy the skill folder (plugins/ca-pi/skills/ca-feature in arbiterForge/codeArbiter) into .agents/skills/ca-feature in your project. Codex loads it when a task matches its description.

Can I use Ca Feature in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add arbiterForge/codeArbiter --skill ca-feature -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ca-feature, .gemini/skills/ca-feature, .github/skills/ca-feature and .opencode/skills/ca-feature in your project.

What does Ca Feature need to run?

SKILL.md names no scripts, command-line tools or credentials: Ca Feature is instructions for the agent only.

Does Ca Feature access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ca Feature safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ca Feature use?

Ca Feature is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ca Feature use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ca Feature?

Skills that share tags, products or a category with Ca Feature: Superpowers Feature Workflow (SYZ-Coder/superpowers-openspec-team-skills, 196 stars), Evanflow Go (evanklem/evanflow, 418 stars), Component Design With Tdad (Habitat-Thinking/ai-literacy-superpowers, 114 stars) and Work Issue (joesaby/astro-mermaid, 123 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ca Feature?

arbiterForge (a GitHub organization) maintains it in arbiterForge/codeArbiter, which has 147 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 5, 2026.

Source: arbiterForge/codeArbiter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.