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 skills add olddustysocksunderthecouch/commit-intent --skill skillgit clone --depth 1 https://github.com/olddustysocksunderthecouch/commit-intentWrote 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.
[](https://agentmods.dev/skills/olddustysocksunderthecouch/commit-intent/skill)<a href="https://agentmods.dev/skills/olddustysocksunderthecouch/commit-intent/skill"><img src="https://agentmods.dev/badge/skills/olddustysocksunderthecouch/commit-intent/skill/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.
<a href="https://agentmods.dev/skills/olddustysocksunderthecouch/commit-intent/skill"><img src="https://agentmods.dev/badge/skills/olddustysocksunderthecouch/commit-intent/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.00779 |
| Opus 5.5 | $0.00027 | $0.00312 |
| Sonnet 5.5 | $0.00013 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
commit-intent 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit intent docs
Every commit in this repo should carry a doc in docs/intents/ recording why the change exists: the user's intent distilled from the AI chats that produced the staged code (primary), key decisions, and a skim of what was built. Generation runs automatically from the repo's pre-commit hook (wired by the commit-intent installer, fail-open) and the doc is staged into the same commit. This skill is the manual entry point to the same engine.
This directory is managed by the commit-intent installer — improvements belong in the commit-intent repo, not here.
Commands
All via Bash, from the repo root:
# Preview: which chats match the currently staged files (no LLM call, no writes)
sh .claude/skills/commit-intent/scripts/generate.sh --dry-run
# Generate for real: writes docs/intents/<local-time>_<slug>.md and stages it
sh .claude/skills/commit-intent/scripts/generate.sh
# Source health check: are Claude Code transcripts and the Cursor DB readable?
sh .claude/skills/commit-intent/scripts/generate.sh --self-test
# Test with simulated staged files (bypasses the index; doc written but NOT staged)
sh .claude/skills/commit-intent/scripts/generate.sh --files=src/foo.ts,src/bar.ts
Environment knobs
INTENT_MODEL— model for the extraction call (defaultsonnet)INTENT_SKIP=1— skip generation for one commit (or usegit commit --no-verify)INTENT_TIMEOUT_MS— LLM call timeout (default90000)INTENT_CLAUDE_BIN— path to the claude binary (default~/.local/bin/claude, then PATH)INTENT_DEBUG=1— verbose matching/scan diagnostics on stderr
How it works
scripts/collect.mjs deterministically finds candidate chats — Claude Code session transcripts under ~/.claude/projects/ (matched by Edit/Write tool calls touching staged files, plus filename mentions) and Cursor composers in its global SQLite store (matched by filename mentions) — within a 14-day window. It builds a redacted, size-capped evidence bundle. scripts/generate.mjs then makes one headless claude -p call (no tools) to distill the doc, writes it with script-owned frontmatter (including staged_diff_sha, the dedupe key), and stages it.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 48 lines · 67 tokens per session scan A 04178f45289d
commit-intent is a skill published in the GitHub repository olddustysocksunderthecouch/commit-intent (11 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 779 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.