agentmods.dev

craft-finish

craft-finish is a skill for Claude Code from Data-Wise/craft. It costs 32 tokens per session (254 once invoked), scanned A, original, MIT.

A coding-session wrap-up tool that records progress in a repository's .STATUS file. It summarizes completed and unfinished work, blockers, checks that were run, and a suggested commit message.

In plain words
What is it for?
Use it when ending a session, saving progress, or preparing a clear handoff without committing or pushing changes.
Why use it?
It preserves enough context to resume later without relying on memory. It also distinguishes verified work from items that have not been checked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the craft plugin — 44 skills, 14 commands, 2 agents, 1 MCP server shipped together

not rated 4repo yesterday A scan 32 tokens original MIT

Good fit Use it when ending a session, saving progress, or preparing a clear handoff without committing or pushing changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/data-wise/craft/craft-finish
View source ↗ Data-Wise/craft data-wise.github.io
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.

Any agent
npx skills add Data-Wise/craft --skill craft-finish
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/craft

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 44 skills, 14 commands, 2 agents, 1 MCP server.

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 craft-finish

README.md
[![agentmods](https://agentmods.dev/badge/skills/data-wise/craft/craft-finish/github.svg)](https://agentmods.dev/skills/data-wise/craft/craft-finish)
Your own site
<a href="https://agentmods.dev/skills/data-wise/craft/craft-finish"><img src="https://agentmods.dev/badge/skills/data-wise/craft/craft-finish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for craft-finish

Your own site · 80×15
<a href="https://agentmods.dev/skills/data-wise/craft/craft-finish"><img src="https://agentmods.dev/badge/skills/data-wise/craft/craft-finish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 254 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.00254
Opus 5.5 $0.00013 $0.00102
Sonnet 5.5 $0.00006 $0.00051
Haiku 4.5 $0.00003 $0.00025

Measured 1mo ago against content hash 413752a2b2eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

craft-finish 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 1mo 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.

openai/craft-openai/skills/craft-finish/SKILL.md · 15 lines

What it actually says

Summarize the current work and preserve enough context to resume.

  1. Read the repository instructions, current .STATUS, working-tree changes, and recent commits. Do not infer completed work from filenames alone.
  2. Summarize completed work in 3–5 plain-language bullets. Identify remaining work and blockers from the observed state.
  3. When the user explicitly asks to finish or save progress, update the existing .STATUS sections for completed work, next action, and blockers. Preserve its format and unrelated content. If there is no .STATUS, draft a concise file with those sections.
  4. Suggest a conventional commit message based on the actual changes. Do not commit, push, or discard changes as part of this skill.
  5. Report verification that was actually run and any remaining unverified item. End with the next action.

Keep the update scoped to session state. Do not run Claude-specific CLAUDE.md or settings synchronization, Obsidian sync, memory tooling, or Craft detectors. Ask before writing .STATUS when the user's intent to save progress is not explicit.

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. 1mo ago First seen · 15 lines · 32 tokens per session scan A 413752a2b2eb

Subscribe to this mod's changes

craft-finish is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 254 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-30.

CI and CDClaude CodeCommitsGit and workflowProductivityadhd-friendlyarchitectureclaude-plugindeveloper-toolkit
Related

craft-finish compared with skills from other repositories

craft-finish next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
craft-finishData-Wise/craftSkill4yesterdayMITA32Claude Code
setup-pre-commitvinvcn/mattpocock-skills-zh-CNSkill5.6k9d agoMITA65Claude Code, Codex
checkpoint-managementa5c-ai/babysitterSkill1.9k5d agoMITA22Claude Code
branch-and-worktree-workflowcbrock84/headcountSkill2.6k19d agoMITA70Claude Code
fix-issueyonatangross/orchestkitSkill299yesterdayMITA45Claude Code
github-operationsyonatangross/orchestkitSkill299yesterdayMITA33Claude Code
swarm-migrateyonatangross/orchestkitSkill299yesterdayMITA103Claude Code