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/rafaelkamimura/claude-tools/commitgit clone --depth 1 https://github.com/rafaelkamimura/claude-toolsWhat 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 | $0.01486 |
| Opus 5 | $0.00000 | $0.00743 |
| Sonnet 5 | $0.00000 | $0.00297 |
| Haiku 4.5 | $0.00000 | $0.00149 |
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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Git Commit Command
Intelligent git commit system that stages only task-related changes and generates meaningful commit messages without AI tool references.
Purpose
- Stage only files related to the current task
- Generate professional commit messages
- Exclude any mention of AI/agent tools
- Maintain clean git history
Execution Steps
Step 1: Check for Task Context
Use Bash tool to find most recent task file:
- Command:
ls -t .claude/task-history/*.md 2>/dev/null | head -1 - Description: "Find most recent task history file"
If no task file exists, output: "No task history found. Proceeding with manual file selection."
If task file exists:
- Use Read tool to read the task file
- Extract: task title, objective, files mentioned, success criteria
Step 2: Analyze Git Status
Use Bash tool to check git status:
- Command:
git status --porcelain - Description: "Check git repository status"
Parse output to categorize:
- Modified files (M prefix)
- Added files (A or ?? prefix)
- Deleted files (D prefix)
- Renamed files (R prefix)
Step 3: Identify Task-Related Files
Based on task context (if available), identify files that:
- Match file patterns from task description
- Are in directories mentioned in task
- Match technology/framework patterns from task
If no task context, consider all changed files as candidates.
Step 4: Present Staging Plan
Output a categorized list of changes:
## Task: [Task Title or "Manual Commit"]
### Will stage:
- file1.js (modified) - implements feature X
- file2.test.js (added) - tests for feature X
### Possibly related (confirm):
- config.json (modified) - may contain task settings
### Will skip:
- .env (modified) - local environment
- debug.log (added) - temporary file
Then output: "Review staging plan. Adjust? (Reply with files to add/remove, or 'ok' to proceed):"
WAIT for user response.
Step 5: Stage Files
Use Bash tool to stage selected files:
- Command:
git add [space-separated file paths] - Description: "Stage task-related files"
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 · 240 lines · 0 tokens per session scan A aec4578f67c6
commit is a command published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,486 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 2026-08-31.
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.