feature

A workflow for taking one feature from its description to tested, reviewed, documented, and committed code. A commit is a saved set of changes in Git.

In plain words
What is it for?
Use it for individual stories or feature requests, including previewing the process, running a lighter version, or completing it without committing changes.
Why use it?
It prevents features from being committed before they pass testing and an evaluator's review, while allowing work to resume from a chosen stage.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/samibs/skillfoundry/feature
Any agent
npx skills add samibs/skillfoundry --skill feature
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,751 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.04751
Opus 5 $0.00011 $0.02375
Sonnet 5 $0.00004 $0.00950
Haiku 4.5 $0.00002 $0.00475

Measured 2d ago against content hash c345931323b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/feature/SKILL.md · 554 lines

How it starts

The opening of the file, as written. The whole thing — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Lifecycle Orchestrator

Role: Per-feature quality pipeline that takes a story or feature description from zero to a committed, documented, tested, and evaluated implementation. No stage is skipped. No commit happens without the evaluator's approval.

Persona: See agents/feature-lifecycle.md for full persona definition.

Activation Syntax

/feature                            Prompt for story or description
/feature STORY-001                  Run lifecycle for a specific story file
/feature "description of feature"   Run lifecycle for an inline description
/feature --dry-run                  Preview pipeline without executing
/feature --from challenge           Resume from a specific stage
/feature --no-commit                Run full pipeline but don't commit
/feature --override "reason"        Accept current gate failure with logged tradeoff
/feature --exec-mode advisory       Force advisory mode (no shell-based test claims)
/feature --detect-stack             Re-run stack detection before starting
/feature --lite                     Lite mode: no shadow tester, no Anvil, single-pass evaluator

Hard Rules

  • NEVER commit before the evaluator gives ✅ or 🟡-resolved verdict
  • NEVER skip the testloop — "it compiles" is not proof
  • NEVER accept evaluator findings as informational — all 🔴 findings produce fix briefs that go back to the coder
  • NEVER write documentation for code that has failing tests
  • NEVER commit unrelated files — stage only the files touched by this feature
  • ALWAYS track state across stages — a failed stage can be resumed
  • STOP and escalate on evaluator verdict 🚫 (full rewrite) — human decision required

State File

All stage state is tracked in .claude/local/feature-state.json:

{
  "story_id": "STORY-001",
  "feature": "User authentication — JWT login flow",
  "stage": "implement | testloop | challenge | document | commit | done | halted",
  "status": "running | success | halted",
  "started_at": "ISO8601",
  "stages": {
    "implement": { "status": "done", "files_modified": ["src/auth/auth.service.ts"] },
    "testloop": { "status": "done", "iterations": 2, "final_pass_rate": "100%" },
    "challenge": {
      "cycles": 2,
      "verdicts": ["🟡", "✅"],
      "fix_briefs_sent": 1,
      "final_verdict": "✅"
    },
    "document": { "status": "done", "files_updated": ["CHANGELOG.md", "docs/api_reference.md"] },
    "commit": { "status": "done", "hash": "abc1234", "message": "feat(auth): JWT login flow [STORY-001]" }
  }
}

Read the full file on GitHub · 554 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 554 lines · 22 tokens per session scan A c345931323b4

Subscribe to this mod's changes

feature is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 4,751 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

ring:applying-composition-patterns

React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…

LerianStudio/ring · 68 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens