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.
npx agentmods add commands/data-wise/craft/finishgit clone --depth 1 https://github.com/Data-Wise/craftWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00008 | $0.00454 |
| Opus 5 | $0.00004 | $0.00227 |
| Sonnet 5 | $0.00002 | $0.00091 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
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 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.
What it actually says
/finish - Session Completion & Context Capture
This command is a thin shim. The canonical behavior lives in the
adhd-workflowskill's Session Completion operation. This file exists only to preserve the explicit/craft:finishslash entry point (renamed from/craft:doneon 2026-07-17 — see ADR-006, which supersedes ADR-002 on naming only; ADR-002's shim-vs-skill rationale is unchanged).
When invoked
-
Load the canonical procedure: read
${CLAUDE_PLUGIN_ROOT:-.}/skills/workflow/adhd-workflow/references/done.mdand follow it exactly. That reference is the single source of truth for the full session-completion flow — CLAUDE.md sync (Step 1.10), Settings Sync (Step 1.10.5), Memory Capture (Step 1.11), Memory Optimize (Step 1.12), Insights Capture (Step 1.13), Worktree Status (Step 1.14), the interactive summary (Step 2), and auto-git (Step 3.5). -
Do not reimplement here. Any change to
/finishbehavior must be made in the reference file, never duplicated into this shim. Keeping the body in one place is the entire point of ADR-002.
Why this is a shim
/finish (renamed from /done) routes to the adhd-workflow skill's Session
Completion operation. Both entry paths — the explicit /craft:finish slash
command and the skill's natural-language match ("wrap up", "I'm done") — route
to the same reference file.
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.
- yesterday First seen · 35 lines · 8 tokens per session scan A bea2e07d4ea5
finish is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 8 tokens to every session and 454 once invoked, about $0.0000 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.
Other commands, from other repositories
readme-audit
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
readme-restructure
Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.
build-fix
Fix build and type failures with minimal diffs.
checkpoint
Record a verified checkpoint before the next phase.
doctor
Check the install surface for missing files and invalid manifests.
feature-dev
Drive a feature from plan to implementation to review.