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/krmcbride/claude-plugins/codereviewgit clone --depth 1 https://github.com/krmcbride/claude-pluginsWhat 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 | $0.00014 | $0.03230 |
| Opus 5 | $0.00007 | $0.01615 |
| Sonnet 5 | $0.00003 | $0.00646 |
| Haiku 4.5 | $0.00001 | $0.00323 |
Grade A, and why
codereview 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 yesterday.
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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeReview Investigation Workflow
Conduct a systematic, multi-step code review of the specified files using the CodeReview methodology. This approach prevents superficial single-pass reviews by enforcing multiple investigation steps with progressive confidence building.
Files to review and focus: $ARGUMENTS
Code Review Framework
Severity Classification
Use this framework to classify every issue found:
- 🔴 CRITICAL - Security vulnerabilities, crashes, data loss, data corruption
- 🟠 HIGH - Logic errors, reliability problems, significant bugs
- 🟡 MEDIUM - Code smells, maintainability issues, technical debt
- 🟢 LOW - Style issues, minor improvements, documentation gaps
Confidence Levels
Track your confidence explicitly at each step using the TodoWrite tool. Progress through these levels as evidence accumulates:
- exploring - Initial code scan, forming hypotheses about issues
- low - Basic patterns identified, many areas unchecked
- medium - Core issues found, edge cases need validation
- high - Comprehensive coverage, findings validated
- very_high - Exhaustive review, minor gaps only
- almost_certain - All code paths checked
- certain - Complete confidence, no further investigation needed
Investigation State
Maintain this state structure throughout the code review:
{
"step_number": 2,
"confidence": "medium",
"findings": [
"Step 1: Found SQL injection vulnerability in auth.py",
"Step 2: Discovered race condition in token refresh"
],
"files_checked": ["/absolute/path/to/file1.py", "/absolute/path/to/file2.py"],
"issues_found": [
{
"severity": "critical",
"description": "SQL injection in user query construction",
"location": "auth.py:45",
"impact": "Attackers can execute arbitrary SQL commands"
}
]
}
Workflow Steps
Step 1: Initial Code Scan (Confidence: exploring)
Focus on:
- Reading specified code files completely
- Understanding structure, architecture, design patterns
- Identifying obvious issues (bugs, security vulnerabilities, performance problems)
- Noting code smells and anti-patterns
- Looking for common vulnerability patterns
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.
- yesterday First seen · 482 lines · 14 tokens per session scan A 967e0b8f9eca
codereview is a command published in the GitHub repository krmcbride/claude-plugins (3 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 3,230 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
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.