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/anilcancakir/claude-codeWrote 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/anilcancakir/claude-code/commit)<a href="https://agentmods.dev/commands/anilcancakir/claude-code/commit"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code/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/anilcancakir/claude-code/commit"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code/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 | $0.00028 | $0.01973 |
| Opus 5.5 | $0.00011 | $0.00789 |
| Sonnet 5.5 | $0.00006 | $0.00395 |
| Haiku 4.5 | $0.00003 | $0.00197 |
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ac:commit
Commit the current working-tree changes as atomic commits using the ac:git-master skill.
Request: $ARGUMENTS
Phase 0: Parse arguments
- Scan
$ARGUMENTSfor--skip-preflight→SKIP_PREFLIGHT = true | false. - Scan
$ARGUMENTSfor--no-push→NO_PUSH = true | false. - Treat any other tokens as free-form note; ignore for now (the commit-style detection in Phase 2 produces the actual message).
Phase 1: Context
Capture the current git state up front so the rest of the command works from real data, not assumptions.
- Current branch: !
git branch --show-current - Working-tree status: !
git status --short - Staged diff stat: !
git diff --staged --stat - Unstaged diff stat: !
git diff --stat - Recent commits (30 for style detection): !
git log -30 --pretty=format:"%h %s" - Upstream tracking: !
git rev-parse --abbrev-ref @{upstream} 2>/dev/null || echo "NO_UPSTREAM" - Merge base with main/master: !
git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null || echo "NO_BASE" - Local-only commits ahead of base: !
git log --oneline $(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)..HEAD 2>/dev/null || echo "NO_BASE"
If the working tree is clean (status output empty), stop with the message Nothing to commit. Working tree clean. and skip every remaining phase.
Phase 2: Preflight (skip if SKIP_PREFLIGHT)
Goal: Catch obvious breakage before writing history.
Skip this phase when SKIP_PREFLIGHT = true. /ac:execute Phase 4 sets this flag because Phase 2d already ran typecheck, build, the full suite and the linter at every wave barrier, and Phase 3a ran them again across the whole project; a third pass here would be the same commands on the same tree.
When SKIP_PREFLIGHT = false:
- Read
CLAUDE.mdandCLAUDE.local.mdif present to find typecheck, test, and lint commands (sections labelledcommands,scripts, or under a "Build / Test / Lint" header). Fall back topackage.jsonscriptsblock when CLAUDE.md does not name the commands. - Run typecheck, then tests, then linter in that order. Each one through
Bash. Use the project's actual commands, not generic guesses. - Pass: continue to Phase 3.
- Fail: stop. Print which preflight step failed and the first ~30 lines of the failure output. Do not commit. The user fixes the issue and re-invokes
/ac:commit.
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 693ebe53f63f
- 22d ago Changed · -29 tokens per session 0749d9d24002
- 1mo ago Changed · -73 tokens per session 3ede5e008210
- 1mo ago First seen · 118 lines · 130 tokens per session scan A fa895f996199
commit is a command published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,973 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
ccc-parallel
Run several Claude Code agents at once, each in its own git worktree and branch, then merge the results through one coordinator. Use when you have independent tasks to develop concurrently.
ccc-pr
Open a pull request for the current branch: commit pending work, run tests, push, and create the PR with gh. Use when a branch is ready for review.
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…
recap
Time-windowed "where was I?" — git commits, session notes, and files touched in the last N hours or days. Use after stepping away for a few hours or days. Not for cold starts after a long absence (use /tools:brief) or live development checks (use /tools:status).
commit
Creates git commits using conventional commit format with appropriate emojis, following project standards and creating descriptive messages that explain the purpose of changes.
create-pr
Streamlines pull request creation by handling the entire workflow: creating a new branch, committing changes, formatting modified files with Biome, and submitting the PR.