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.
git clone --depth 1 https://github.com/outfitter-dev/blzWrote 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/outfitter-dev/blz/cli-test)<a href="https://agentmods.dev/commands/outfitter-dev/blz/cli-test"><img src="https://agentmods.dev/badge/commands/outfitter-dev/blz/cli-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/outfitter-dev/blz/cli-test"><img src="https://agentmods.dev/badge/commands/outfitter-dev/blz/cli-test.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00009 | $0.00483 |
| Opus 5.5 | $0.00004 | $0.00193 |
| Sonnet 5.5 | $0.00002 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
cli-test 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blz CLI Comprehensive Test
Please perform a comprehensive test of the blz CLI tool with the following focus: $ARGUMENTS
Test Plan
1. Environment & Setup
- Verify
blzis properly installed and accessible - Check version information with
blz --version - Validate configuration directory structure
- Test help output for main command and subcommands
2. Core Functionality Tests
- Search Operations: Test various search patterns, filters, and output formats
- Source Management: Add, list, update, and remove sources
- Index Operations: Test indexing, updates, and cache management
- Configuration: Verify config file handling and environment variables
3. Edge Cases & Error Handling
- Invalid input validation
- Network connectivity issues
- Corrupted cache handling
- Permission errors
- Large dataset performance
4. Output Format Testing
- Text output formatting and readability
- JSON output structure and validity
- Error message clarity and helpfulness
- Search result relevance and ranking
5. Integration Testing
- Shell completion functionality
- Pipe/redirection compatibility
- Exit codes for scripting
- Configuration precedence (env vars vs config files)
Expected Deliverables
- Test Summary: Overall health status of the CLI
- Performance Metrics: Search latency, indexing speed, memory usage
- Issue Report: Any bugs, inconsistencies, or UX problems found
- Improvement Suggestions: Specific recommendations with priority levels
Special Instructions
- Use verbose output (
-vor--verbose) when available to capture detailed logs - Test with both small and large document sets if possible
- Verify that all documented features work as described in help text
- Pay attention to consistency across similar commands (flags, output format, etc.)
- Test error recovery and graceful degradation scenarios
If you identify any issues, please:
- Document exact reproduction steps
- Include relevant error messages or unexpected outputs
- Suggest specific fixes or improvements
- Prioritize issues by severity (critical, high, medium, low)
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.
- 1mo ago First seen · 65 lines · 9 tokens per session scan A 904c7dd09e90
cli-test is a command published in the GitHub repository outfitter-dev/blz (27 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 483 once invoked, about $0.0000 per session on Opus 5.5. 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
verify
Run the full verification pipeline (scripts/verify-all.sh) and fix failures until every stage is green.
grade
Grade an MCP server A–F with the open polygraph litmus (runs the harness).
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
iai-directive
Record, list, or remove a standing order the user typed themselves.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.