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/thedecipherist/claude-code-mastery/reviewgit clone --depth 1 https://github.com/TheDecipherist/claude-code-masteryWhat 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 | $0.00396 |
| Opus 5 | $0.00005 | $0.00198 |
| Sonnet 5 | $0.00002 | $0.00079 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
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 3d 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.
What it actually says
Code Review
Review the current changes systematically.
1. Get the Changes
git diff --staged
If nothing is staged, check unstaged changes:
git diff
2. Review Checklist
For each changed file, evaluate:
Correctness
- Logic is correct and handles edge cases
- No off-by-one errors
- Null/undefined handled properly
- Async operations awaited correctly
- Error paths don't leave state inconsistent
Security
- No hardcoded secrets or credentials
- User input is validated/sanitized
- No SQL injection vulnerabilities
- No XSS vulnerabilities
- Sensitive data not logged
Performance
- No N+1 query patterns
- No unnecessary re-renders (React)
- Large lists are paginated or virtualized
- Expensive operations are memoized where appropriate
Maintainability
- Code is readable without excessive comments
- No magic numbers (use constants)
- Functions do one thing
- No dead code
3. Output Format
For each issue found:
**[SEVERITY]** filename:line_number
Issue: <description>
Suggestion: <how to fix>
Severity levels:
- CRITICAL — Must fix before merge (security, data loss, crashes)
- HIGH — Should fix (bugs, performance issues)
- MEDIUM — Consider fixing (code smell, maintainability)
- LOW — Optional (style, minor improvements)
4. Summary
End with:
- Total issues by severity
- Overall assessment (approve / request changes)
- Any praise for well-written code
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.
- 3d ago First seen · 73 lines · 11 tokens per session scan A 4403eb353a5a
review is a command published in the GitHub repository TheDecipherist/claude-code-mastery (545 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 396 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
maintainer-review-code-review
Review the PR for code quality, CLAUDE.md compliance, project conventions, and bugs (Pi-tuned).
maintainer-review-synthesize
Synthesize findings from all review aspects into a single maintainer-ready review report (Pi-tuned).
review-synthesize
Produce one evidence-based verdict, write the review report humans read, and publish it when the scope is a PR. You are read-only: never modify project files or commit; your only write outside the artifacts directory is the PR comment below. Read-only extends past the repository: a falsifying command creates its own…
triage
Confirm whether the work item still names real current work, choose the kind of reasoning owed next, and stop. Write the decisive evidence and handoff to $ARTIFACTSDIR/triage.md. You assess and route only: the repository must be exactly as you found it when you finish. No one watches the run; the report and your…
review-docs
Find one defect: after this change, someone following the repository's documentation would form a materially wrong expectation or lack a required step. Wrong documentation is worse than missing documentation; unnecessary documentation is maintenance debt. Read-only: never modify files, commit, or post anywhere.
deploy
Deploy Solana program (devnet first, then mainnet).