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/reviewprgit clone --depth 1 https://github.com/awattar/claude-code-best-practicesWrote 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/awattar/claude-code-best-practices/reviewpr)<a href="https://agentmods.dev/commands/awattar/claude-code-best-practices/reviewpr"><img src="https://agentmods.dev/badge/commands/awattar/claude-code-best-practices/reviewpr.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00851 |
| Opus 5 | $0.00006 | $0.00426 |
| Sonnet 5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
reviewpr 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code User Command: Reviewpr
This command helps you thoroughly review GitHub pull requests specified in $ARGUMENTS.
Usage
To review a pull request, just type:
/reviewpr <pr-number>
What This Command Does
- Fetches PR details and diff for $ARGUMENTS using GitHub CLI (
gh). - Checks CI/CD status and checks out the PR locally.
- Reviews code quality, observability, and tests the changes.
- Documents findings in a scratchpad and submits review via GitHub CLI (
gh). - Monitors for author responses and re-reviews as needed.
Agents Used
This command leverages specialized agents for comprehensive pull request review:
- general-code-quality-debugger - Essential for systematic code review and quality assessment
- general-technical-project-lead - For security assessments and architectural review
- general-qa - For testing validation and edge case identification
- general-solution-architect - For reviewing architectural decisions and patterns
Each agent contributes specialized expertise to ensure thorough project analysis and high-quality documentation generation.
Follow these steps:
General
Follow GitHub flow and code review best practices - https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/reviewing-changes-in-pull-requests
Before starting:
- Identify the project's test framework and browser automation tools (e.g., puppeteer, playwright, selenium) for testing UI change via MCP. Check project documentation or ask if unclear.
- Remember to use the GitHub CLI (
gh) for all PR-related tasks.
Analyze
Gather context and understand the PR:
- Use
gh pr viewto get the PR details and description. - Use
gh pr diffto review the changes in detail. - Check the PR against the original issue requirements:
- Use
gh pr view --json body,title,numberto get linked issues. - Verify all acceptance criteria are met.
- Use
- Search scratchpads for any design decisions or context related to this PR.
- Use
gh pr checksto verify CI/CD status.
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.
- 5d ago First seen · 109 lines · 13 tokens per session scan A 1dc88bde6e51
reviewpr is a command published in the GitHub repository awattar/claude-code-best-practices (251 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 851 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.