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.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/commit)<a href="https://agentmods.dev/commands/sigistry/marketplace/commit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/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/commands/sigistry/marketplace/commit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/commit.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 | $0.00011 | $0.00730 |
| Opus 5.5 | $0.00004 | $0.00292 |
| Sonnet 5.5 | $0.00002 | $0.00146 |
| Haiku 4.5 | $0.00001 | $0.00073 |
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 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn the currently staged diff into one well-formed Conventional Commit message, ready to paste into git commit. Use this right before committing when you want a clean, conventional message that explains the why. Reads only what is staged (git diff --cached).
Process
Step 1: Confirm something is staged
Run git diff --cached --stat. If it is empty, there is nothing to commit, run git status --short to show the user what is unstaged/untracked, remind them to git add, and STOP. Do not invent a message from unstaged work.
Step 2: Read the staged diff
git diff --cached: the full staged patch. Read it to understand what actually changed.git status --short: to note anything left unstaged that arguably belongs in this commit (mention it, but only describe what IS staged).
Step 3: Classify the change type
Pick the single best type per the changelog-assembly skill's references/conventional-commits.md:
| Type | When |
|---|---|
feat |
A new user-facing capability |
fix |
A bug fix |
docs |
Documentation only |
style |
Formatting/whitespace, no logic change |
refactor |
Behavior-preserving restructuring |
perf |
A performance improvement |
test |
Adding/fixing tests only |
build |
Build system, deps, packaging |
ci |
CI configuration/pipelines |
chore |
Maintenance not touching src or tests |
revert |
Reverting a prior commit |
If a diff spans multiple types, pick the dominant one and note that splitting into separate commits may be cleaner.
Step 4: Derive scope, subject, body, footers
- Scope (optional): the module/package/area most affected (e.g.
auth,parser,api). Derive it from the top-level directory or component in the diff. - Subject: imperative mood, ≤50 characters, no trailing period, lowercase after the colon.
- Body: wrap at ~72 columns; explain why and any non-obvious how. Omit for trivial changes.
- Footers: add
BREAKING CHANGE: <description>(and a!after type/scope) if a public contract changed; addCloses #NN/Refs #NNif the diff or branch name references an issue.
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 · 62 lines · 11 tokens per session scan A b3709bb72fcc
commit is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 730 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 2026-09-03.
Other commands, from other repositories
commit
Create well-formatted commits with conventional commit messages and emojis.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…
copush
Pull, version-bump, commit all changes, and push to origin.
commit-push-pr
Complete workflow — commit, push, and create a pull request in one step.
commit
Create a git commit with an automatically generated message based on staged and unstaged changes.
diff-review
Generate a visual HTML diff review — before/after architecture comparison with code review analysis.