feature

feature is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (4,720 once invoked), scanned A, original, MIT.

A per-feature workflow that takes a story or feature description through implementation, testing, documentation, evaluation, and an optional commit. A story is a short description of a piece of work from a user's or product's perspective.

In plain words
What is it for?
Use it to start or resume feature work, preview the workflow, run without committing, detect the technology stack again, or choose a lighter evaluation mode.
Why use it?
It gives each feature a consistent set of checks and prevents code from being committed before an evaluator reviews it.

Command for Claude Code

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 commands/samibs/skillfoundry/feature
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for feature

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/feature.svg)](https://agentmods.dev/commands/samibs/skillfoundry/feature)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/feature"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,720 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 $0.00000 $0.04720
Opus 5 $0.00000 $0.02360
Sonnet 5 $0.00000 $0.00944
Haiku 4.5 $0.00000 $0.00472

Measured yesterday against content hash 677fa7fa998c, 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 yesterday.

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.

.claude/commands/feature.md · 548 lines

How it starts

The opening of the file, as written. The whole thing — 548 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 · 548 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. yesterday First seen · 548 lines · 0 tokens per session scan A 677fa7fa998c

Subscribe to this mod's changes

feature is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,720 tokens. 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 2026-09-03.