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/ttktjmt/mjswan/commit-messagegit clone --depth 1 https://github.com/ttktjmt/mjswanWhat 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 | $0.00011 | $0.00247 |
| Opus 5 | $0.00005 | $0.00123 |
| Sonnet 5 | $0.00002 | $0.00049 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
commit-message 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 today.
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
Context
- Current git status: !
git status - Current git diff (staged and unstaged changes, excluding lockfiles): !
git diff HEAD -- ':!package-lock.json' ':!uv.lock'
Your task
Based on the above changes, output a concise and descriptive commit message following these rules:
- Use the imperative mood (e.g. "Add", "Fix", "Update", "Remove")
- Keep the subject line under 72 characters
- Write in English
- Avoid vague words like "change", "update files", or "fix stuff"
- Default to a single subject line. Only add a body if the changes are genuinely large and span multiple unrelated concerns that cannot be summarized in one line.
- If a body is needed, separate it from the subject with a blank line and use short bullet points.
Output only the commit message itself — no explanations, no extra text.
Do NOT run git commit or any other write operation. Only read and suggest.
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.
- today First seen · 25 lines · 11 tokens per session scan A 14d3ffd5f247
commit-message is a command published in the GitHub repository ttktjmt/mjswan (325 stars, last pushed 2d ago), licensed Apache-2.0. It adds 11 tokens to every session and 247 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 2026-09-01.
Other commands, from other repositories
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes. Invoke with /create-pr.
review-pr
Intelligent PR code review with dynamic agent allocation based on domains and signals.
gen-commit-msg
Generate intelligent commit messages based on staged changes. Invoke with /gen-commit-msg.
dart-resume
Command "dart-resume" from dartsim/dart, covering objective, argument handling, required reading, workflow and recon (no changes).
dart-next
Select and execute the next bounded DART task: $ARGUMENTS.
dart-pr
create a branch, commit, push, and open a DART pull request.