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/anilcancakir/claude-code-plugins/my_reviewgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWrote 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-plugins/my_review)<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugins/my_review"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugins/my_review.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 | $0.00020 | $0.01086 |
| Opus 5 | $0.00010 | $0.00543 |
| Sonnet 5 | $0.00004 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
my_review 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Command
Review all uncommitted changes before committing. Analyzes code for bugs, security vulnerabilities, quality issues, and test coverage.
Arguments
Parse from $ARGUMENTS:
- --code-only: Skip test analysis
- --test-only: Only run test coverage analysis
- --security-only: Focus on security issues only
- --auto-fix: Automatically fix simple issues (formatting, obvious bugs)
Default (no args): Full review + test analysis + auto-fix simple issues.
Execution Steps
Step 1: Get Changes
# Unstaged changes
git diff --name-only
# Staged changes
git diff --cached --name-only
# Combined diff for analysis
git diff HEAD
Step 2: Detect Project Stack
Check for stack indicators:
composer.json+artisan= Laravelpubspec.yaml= Flutternuxt.config.*= Nuxt.jspackage.jsonwith "vue" = Vuetailwind.config.*= TailwindCSSpackage.jsonwith "alpinejs" = Alpine.js
Step 3: Launch Review Agents
Use the Task tool to spawn agents in parallel:
// 1. Code Review (Opus - deep analysis)
Task({
subagent_type: "code-reviewer",
prompt: `Review the uncommitted changes in this repository.
Focus on: security, bugs, logic errors, code quality.
Stack context: ${DETECTED_STACK}
Changes: ${GIT_DIFF_OUTPUT}`
})
// 2. Test Coverage (Sonnet - if not --code-only)
Task({
subagent_type: "test-checker",
prompt: `Analyze test coverage for uncommitted changes.
Check for: missing tests, bug fix regression tests.
Changed files: ${CHANGED_FILES}`
})
Step 4: Process Results
Collect findings from both agents and categorize:
| Severity | Auto-Fix | Action |
|---|---|---|
| Critical | No | Block commit, require fix |
| Warning | If --auto-fix | Fix or report |
| Suggestion | If --auto-fix | Fix or note |
Step 5: Auto-Fix (if enabled)
Simple issues to fix automatically:
- Missing null checks (add guard clause)
- Obvious type coercion bugs
- Missing CSRF tokens in forms
- Unescaped output (add escape function)
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 · 174 lines · 20 tokens per session scan A 5477e4aca54d
my_review is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 1,086 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 2026-08-31.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
create-hook
Create a new custom automation hook.
health
Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.
plan-new
Plan a complex project with discovery, structure, and kill criteria.
remember
Explicitly save something to memory as an experience.
review
Structured code review with severity categorization (distinct from Claude Code's PR review).