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 mrclrchtr/supi --skill commitgit clone --depth 1 https://github.com/mrclrchtr/supiWrote 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/mrclrchtr/supi/commit)<a href="https://agentmods.dev/skills/mrclrchtr/supi/commit"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/commit/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/mrclrchtr/supi/commit"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00007 | $0.00625 |
| Opus 5.5 | $0.00003 | $0.00250 |
| Sonnet 5.5 | $0.00001 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
commit 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit candidate
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
Guardrails
- Inspect candidate changes for credentials, private keys, tokens, and local secret files. STOP and ask what to do without repeating the secret value.
- Preserve changes outside the current task. Ask before changing an existing staged change that is outside the task boundary.
- Keep normal Git hooks enabled.
- Do not use sub-agents.
Process
-
Establish the Git state. Inspect the branch, active Git operation, staged and unstaged changes, untracked files, and the task or issue boundary. Ask when required facts are unclear.
Done when: the request mode, task boundary, and Git state are understood.
-
Build the commit candidate. Stage only changes that directly belong to the task or issue. Preserve unrelated staged changes. If the task forms one coherent change, prepare one candidate. Ask when grouping is unclear. If there is no suitable candidate, report it and stop.
Done when: the staged patch contains the complete intended change and no unrelated change.
-
Audit the candidate. Inspect the full staged diff, check for possible secrets, and run
git diff --cached --check. Let normal Git hooks run when creating the commit. Fix and retry only an obvious mechanical failure inside the task; otherwise stop and report the failure.Done when: the diff audit passes and all hook results are known.
-
Write the message. Match recent commit history first. Honor explicit message requirements. Use a concise subject with the repository's normal type, scope, mood, length, and punctuation. Add a body only when it explains why, a trade-off, a constraint, a side effect, or a required follow-up. Add references to tickets if they exist; don't invent them.
-
Create the requested commit. For a normal commit, pass the complete message through a quoted heredoc:
What ships with it
1 file 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.
- today Changed · +5 lines 5da30bd17189
- 1mo ago Changed 12146fbaa618
- 1mo ago First seen · 45 lines · 7 tokens per session scan A 151554dc2fac
commit is a skill published in the GitHub repository mrclrchtr/supi (98 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 625 once invoked, about $0.0000 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
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-platform
GitHub pull requests, review threads, failing Actions checks and stacked pull requests, through GitHub's MCP server and the gh CLI. Use when opening, reviewing or updating a pull request, fixing a failed check, or splitting a change into a stack.
gitlab-platform
GitLab merge requests, review threads, failed pipelines and stacked merge requests, through GitLab's MCP server and the glab CLI. Use when opening, reviewing or updating a merge request, fixing a failed pipeline, or splitting a change into a stack.
yeet
Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with gh used only as a fallback where connector coverage is insufficient.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
pr-comment-resolver
Addresses PR review comments by implementing requested changes and reporting resolutions. Use when code review feedback needs to be resolved with code changes.