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/signalcompose/claude-toolsWrote 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/signalcompose/claude-tools/commit)<a href="https://agentmods.dev/commands/signalcompose/claude-tools/commit"><img src="https://agentmods.dev/badge/commands/signalcompose/claude-tools/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/signalcompose/claude-tools/commit"><img src="https://agentmods.dev/badge/commands/signalcompose/claude-tools/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 | $0.00009 | $0.01096 |
| Opus 5.5 | $0.00004 | $0.00438 |
| Sonnet 5.5 | $0.00002 | $0.00219 |
| Haiku 4.5 | $0.00001 | $0.00110 |
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chezmoi Commit
Overview
Detect changed dotfiles, commit and push to remote.
Capabilities:
- Detects changed dotfiles
- Creates commit with user confirmation
- Pushes to remote repository
Use when: "commit dotfiles", "push dotfiles", "save dotfile changes", "backup dotfiles", "dotfilesコミット", "dotfiles反映", "dotfiles保存"
Don't use for: Project code commits, general git operations, non-dotfile changes
Flow:
status → diff → confirm → chezmoi add → git add → commit → push
Execution
Step 1: Detect & Show Changes
Run chezmoi status and chezmoi diff --reverse. If no changes, report and exit.
Step 2: Confirm with User
Present detected changes and ask for confirmation before proceeding.
Step 3: Add, Commit & Push
Add files with chezmoi add, then commit and push from ~/.local/share/chezmoi.
Reference: Diff Interpretation
Recommended: Use --reverse Flag
For /chezmoi:commit, always use:
chezmoi diff --reverse
This produces git-like output that shows what commit will do:
-lines will be removed from source+lines will be added to source
No special interpretation rules needed. Read it like a normal git diff.
Why --reverse?
Normal chezmoi diff (without flag)
Shows what chezmoi apply would do (making local match source):
-= current content in LOCAL (destination)+= desired content from SOURCE (target state)
This is counterintuitive when committing (local → source).
chezmoi diff --reverse
Shows what commit will do (local → source):
-= will be removed from source+= will be added to source
This matches git diff semantics exactly.
Example Comparison
Local has hookify, source has sigcomintra:
Without --reverse:
- "hookify@...": true, ← Local has this
+ "sigcomintra@...": true, ← Source has this
Confusing: - means "will be added to source" (counterintuitive)
With --reverse:
- "sigcomintra@...": true, ← Will be removed from source
+ "hookify@...": true, ← Will be added to source
Clear: Standard git diff semantics
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 · 178 lines · 9 tokens per session scan A f5132b97a4dc
commit is a command published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,096 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 2026-08-31.
Other commands, from other repositories
standup
Review my git commits from the past workday and generate a standup summary.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.
commit
Context-aware Git commit assistant with smart pre-commit checks.