feature-done

feature-done is a skill for Claude Code, Codex from shrekshrek/project-workflow. It costs 28 tokens per session (341 once invoked), scanned A, original, MIT.

A completion check for a finished software feature, covering project checks, conventions, requested changes, current state, and a delivery record.

In plain words
What is it for?
Use it at the end of a feature to review the relevant Git changes, run the required reviews, record the result, and identify next steps if it is not ready.
Why use it?
It helps reveal missing checks or unresolved requirements before a feature is handed over.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the project-workflow plugin — 9 skills, 6 agents shipped together

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/shrekshrek/project-workflow/feature-done
Any agent
npx skills add shrekshrek/project-workflow --skill feature-done
Clone the repo
git clone --depth 1 https://github.com/shrekshrek/project-workflow

Made for: Claude Code, Codex.

Or install project-workflow, the plugin that ships this one along with the rest of its 9 skills, 6 agents.

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-done

README.md
[![agentmods](https://agentmods.dev/badge/skills/shrekshrek/project-workflow/feature-done.svg)](https://agentmods.dev/skills/shrekshrek/project-workflow/feature-done)
Your own site
<a href="https://agentmods.dev/skills/shrekshrek/project-workflow/feature-done"><img src="https://agentmods.dev/badge/skills/shrekshrek/project-workflow/feature-done.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 341 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 $0.00028 $0.00341
Opus 5 $0.00014 $0.00170
Sonnet 5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 4d ago against content hash fdc7cee3087e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-done 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 4d 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.

adapters/claude/skills/feature-done/SKILL.md · 21 lines

What it actually says

Feature Done

Match the user's language. Read ${CLAUDE_PLUGIN_ROOT}/docs/actions/feature-done.md completely before acting. Fresh reviewer agents read their canonical specs; the main session reads one only when executing the allowed fallback.

Claude execution details:

  • Resolve $ARGUMENTS through the shared active-feature rules; exclude archive/. Review applicability follows the actual risk and project requirements, not file names.
  • Execute the complete canonical action with Bash against its selected Git population. A stop still writes the canonical receipt.
  • Resolve the canonical convention population and dispatch spec-reviewer and agents-md-reviewer as directed. Claude L2 may include project-root .claude/rules/; include user-level ~/.claude/rules/ only when selected.
  • Capture the reviewed Git identity before endpoint-owned writes, then persist and structurally re-read the canonical ## Proof Bundle receipt. For a non-READY verdict, map each blocker or blocker group to the canonical Next route before returning control under the action's continuation rules. Return the action's concise human summary with Lifecycle: READY; archive pending when applicable and a repository-relative link to the resolved receipt (default spec.md#proof-bundle); the full receipt remains on disk.

Apply the canonical verdict contract. Finish/delivery stops at READY with archive pending; enclosing close/archive/submit intent continues to /project-workflow:feature-archive for the explicit feature.

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. 4d ago First seen · 21 lines · 28 tokens per session scan A fdc7cee3087e

Subscribe to this mod's changes

feature-done is a skill published in the GitHub repository shrekshrek/project-workflow (2 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 341 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 2026-08-31.

Related

Other skills, from other repositories

iso-24495-2

Sector-specific Plain Language standard for legal communication (ISO 24495-2:2025). Applied during contract drafting, license review, and legal/compliance writing.

GaZmagik/iso-24495 · 40 tokens

configuration-management

Secrets management, environment-specific configs, safe defaults, feature flags, configuration-as-code, compliance and audit trails. Use when managing secrets, configuring deployments, or implementing feature flags.

saitarrun/Devforge-ai · 38 tokens

dependency-management

Version updates (major/minor/patch), security patch application, transitive dependency resolution, monorepo dependency management, deprecation tracking, license compliance. Use when updating dependencies, managing versions, or addressing CVEs.

saitarrun/Devforge-ai · 47 tokens

motherduck-security-governance

Explain MotherDuck security, governance, and access-control patterns. Use for any question about SOC 2, GDPR, compliance, data residency, regions, SSO, service accounts, token handling, tenant isolation, sharing boundaries, snapshots and recovery, or governance posture — including when a securitycomplianceowner…

motherduckdb/agent-skills · 79 tokens

Amend

Formally amend the constitution, with mandatory impact analysis before any change lands. The constitution is supreme law; amendments are versioned and their downstream effects scanned first.

Nagiliant/Genesis-Legacy-V2 · 35 tokens

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens