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/aidotnet/opencowork/commitgit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWhat 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 | $0.00000 | $0.00527 |
| Opus 5 | $0.00000 | $0.00264 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00053 |
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 2d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Conventional Commits style messages and commit the current repository's uncommitted changes, grouped by logical classification.
Execution requirements
- First collect enough evidence before writing commit messages.
- Inspect the current uncommitted changes: staged changes, unstaged changes, and newly added files.
- Read enough of the changed files to understand the purpose of the changes instead of relying only on filenames.
- If helpful, inspect recent commit history for repository-specific wording patterns, but the final messages should follow Conventional Commits style.
- Treat any user text that follows the command as additional emphasis or constraints for the draft.
- Default scope is all current uncommitted changes.
- Group changes by logical classification: analyze the changes and split them into groups by type (e.g.,
docs,feat,fix,refactor,style,chore). Each group becomes a separate commit. - For each group: stage only the relevant files with
git add <paths>, then rungit commitwith the message for that group. Execute commits in a sensible order (e.g., refactor before feat, docs last). - For commits created by this command, use
[email protected]as the committer email (set per command, e.g.git -c [email protected] commit ...; do not change global git config).
Commit drafting rules
- Infer the most appropriate Conventional Commits type from the actual changes, such as
feat,fix,refactor,perf,docs,test,build,ci,chore, orstyle. - Include a
scopeonly when it can be inferred clearly and usefully from the changed area. If the scope is unclear, omit it. - Keep the subject concise, imperative, and specific.
- Add a short body only when it helps clarify the change.
- Do not generate multiple alternatives per group unless the user explicitly asks for them.
Output requirements
Produce the result in this structure (then execute the commits as described in Execution requirements):
Change Summary
- One sentence per commit group summarizing the purpose of that group.
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.
- 2d ago First seen · 41 lines · 0 tokens per session scan A 2d934564f208
commit is a command published in the GitHub repository AIDotNet/OpenCowork (632 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 527 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.