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/outfitter-dev/blz/reviewgit clone --depth 1 https://github.com/outfitter-dev/blzWhat 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 | $0.00008 | $0.00668 |
| Opus 5 | $0.00004 | $0.00334 |
| Sonnet 5 | $0.00002 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
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 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blz Code Review
Please perform a comprehensive code review of: $ARGUMENTS
Review Focus Areas
1. Rust Code Quality
- Safety: Check for unsafe blocks, unwrap(), panic!(), and other dangerous patterns
- Performance: Identify potential bottlenecks, unnecessary allocations, or inefficient patterns
- Error Handling: Verify proper error propagation and user-friendly error messages
- Memory Management: Look for potential leaks or inefficient memory usage
- Async Patterns: Check async/await usage follows project conventions
2. Architecture & Design
- Separation of Concerns: Ensure blz-core, blz-cli, and blz-mcp boundaries are respected
- API Design: Check for consistency with existing patterns and interfaces
- Configuration: Verify proper handling of config files and environment variables
- Testing: Ensure adequate test coverage for new functionality
3. CLI-Specific Concerns
- User Experience: Check command line interface consistency and usability
- Help Text: Verify documentation accuracy and completeness
- Output Formatting: Ensure consistent text and JSON output formats
- Backward Compatibility: Flag any breaking changes to existing commands
4. Performance Impact
- Search Latency: Ensure changes don't negatively impact search performance
- Index Building: Check that indexing speed remains within acceptable bounds
- Memory Usage: Verify no significant memory footprint increases
- Startup Time: Ensure CLI startup remains fast
5. Security & Robustness
- Input Validation: Check for proper validation of user inputs
- File System Access: Verify safe handling of file operations
- Network Requests: Check HTTP client usage and error handling
- Data Integrity: Ensure cache and index data integrity is maintained
Review Deliverables
Please provide:
- Executive Summary
- Overall assessment of code quality
- Major concerns or blockers
- Recommendation (approve/request changes/block)
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 · 82 lines · 8 tokens per session scan A 4d232254a54e
review is a command published in the GitHub repository outfitter-dev/blz (27 stars, last pushed 21d ago), licensed MIT. It adds 8 tokens to every session and 668 once invoked, about $0.0000 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
CAA-add
Add a valuable fix/insight from this session to the Claude Archive (CAA) — give, score honestly, sync.
CAA-search
Search the Claude Archive (CAA) for scored solutions BEFORE solving — take the best hit, verify, apply.
CAA-add-latest
Instantly archive the LATEST hard-won fix from this session to the Claude Archive (CAA) — zero questions.
template
Manage issue templates for streamlined issue creation.
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
security-review
CWE 기반 보안 검토 + STRIDE 위협 모델링 (v6 - effort:max 강제).