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/awattar/claude-code-best-practices/commitgit clone --depth 1 https://github.com/awattar/claude-code-best-practicesWhat 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 | $0.00011 | $0.00524 |
| Opus 5 | $0.00005 | $0.00262 |
| Sonnet 5 | $0.00002 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00052 |
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code User Command: Commit
This command helps you create well-formatted commits with conventional commit messages.
Usage
To create a commit, just type:
/commit
What This Command Does
- Checks which files are staged with
git status. - If 0 files are staged, automatically adds all modified and new files with
git add. - Performs a
git diffto understand what changes are being committed. - Analyzes the diff to determine if multiple related logical changes are present.
- If multiple related changes are detected, breaks the commit message into multiline message.
Agents Used
This command leverages two specialized agents for optimal results:
- general-code-quality-debugger - For analyzing code changes and ensuring commit quality
- general-technical-project-lead - For strategic decisions about commit structure and breaking changes
Each agent contributes expertise to ensure high-quality commits that follow best practices and maintain project standards.
Best Practices for Commits
IMPORTANT: The /commit command always follows standardized commit conventions and best practices. For detailed formatting rules and guidelines, refer to:
Commit Format Templates
- Format reference: @.gitmessage - Complete commit message format specification with examples
- Best practices: @.github/COMMIT_CONVENTION.md - Detailed guidelines for atomic commits, splitting commits, and workflow integration
Key Conventions
- Conventional commit format: Follows standardized format with issue linking
- Atomic commits: Each commit serves a single logical purpose
- Format enforcement: Automatic validation of commit message structure
- Issue integration: Automatic detection and formatting of GitHub issue references
Setup Git Template (Optional)
To use the commit message template with standard git commands:
git config commit.template .gitmessage
This will populate the commit message editor with the template format when using git commit without the -m flag.
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 · 62 lines · 11 tokens per session scan A a015a78b9401
commit is a command published in the GitHub repository awattar/claude-code-best-practices (250 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 524 once invoked, about $0.0001 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 2026-08-30.
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.