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/blendsdk/claude-codeops/gitcmgit clone --depth 1 https://github.com/blendsdk/claude-codeopsWhat 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 | $0.00034 | $0.00761 |
| Opus 5 | $0.00017 | $0.00380 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
gitcm 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gitcm — commit with a detailed message
Stage all changes and create one well-formed commit. Do not push.
Current state
- Status: !
git status --short - Staged/unstaged diff stat: !
git diff HEAD --stat
Steps
- Clean-tree guard. If
git status --shortprints nothing, report "nothing to commit" and stop — do not run verify or stage. - Verify first. Run the project's verify command (build + test) as defined in the
project's
CLAUDE.md(or detected conventions). Only continue if it passes. If it fails, stop and report — do not commit broken code. If the project has no verify command, say so and continue. - Stage deliberately. Glance at the untracked files in the status first — anything that
looks like secrets, scratch files, or build output gets flagged to the user before staging.
Then
git add .— noting it is CWD-relative: in a monorepo subdirectory it stages only the subtree; run it from the intended root. - Write the commit message to a file, never inline. Compose a Conventional Commit
message and write it to
.git/COMMIT_EDITMSG_codeops(or a temp file) with the Write tool, then commit withgit commit -F <file>. Never usegit commit -m— inline messages break on quotes, parentheses,$, backticks, and multi-line bodies. - Pre-commit hooks. If a hook modifies files during the commit, re-stage the modified
files and retry ONCE; if the hook fails, show its output and ask — never pass
--no-verifywithout the user's explicit approval. - Clean up the temp message file after a successful commit.
- Report the resulting commit (
git log -1 --stat).
If the user passed $ARGUMENTS, use it as a hint for the scope or emphasis.
Commit message format (Conventional Commits)
<type>(<scope>): brief description in the imperative
- Specific change 1
- Specific change 2
- Tests added/updated
- Verification: passing
Types: feat, fix, refactor, test, docs, chore.
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.
- yesterday First seen · 64 lines · 34 tokens per session scan A 40a54bd09ec2
gitcm is a command published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 761 once invoked, about $0.0002 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 2026-08-31.
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.