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 skills/outfitter-dev/blz/blz-docs-searchnpx skills add outfitter-dev/blz --skill blz-docs-searchgit 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/skills/outfitter-dev/blz/blz-docs-search)<a href="https://agentmods.dev/skills/outfitter-dev/blz/blz-docs-search"><img src="https://agentmods.dev/badge/skills/outfitter-dev/blz/blz-docs-search.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 | $0.00068 | $0.00721 |
| Opus 5 | $0.00034 | $0.00360 |
| Sonnet 5 | $0.00014 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
blz-docs-search 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BLZ Search Patterns
Fast local documentation search using blz. Search is local, free, and fast (~6ms) - try many queries.
Key Concepts
Full-text search, not semantic: blz uses BM25 ranking. Query with keywords that appear in docs:
- Good:
"useEffect cleanup","test configuration","HTTP server" - Bad:
"How do I use useEffect?","What's the best way to..."
Citations: Results include citations like bun:304-324 (source:start-end lines). Use these with blz find to retrieve content.
Quick Patterns
# Check available sources first
blz list --status --json
# Basic search
blz "test runner" --json
# Search specific source
blz "hooks" --source react --json
# Retrieve by citation
blz find bun:304-324 --json
# Retrieve with full section context
blz find bun:304-324 --context all --json
# Retrieve with surrounding lines
blz find bun:304-324 -C 5 --json
# Batch retrieve multiple citations
blz find bun:304-324 deno:500-520 --json
Search Strategy
- Start specific: Use precise technical terms
- Try variations: Synonyms, abbreviations, alternate terms
- Check sources: Verify relevant docs are indexed
- Multiple searches: Run 3-5 different queries - it's fast
- Narrow by source: Use
--sourcewhen you know the library
Retrieval Options
| Flag | Use When |
|---|---|
--json |
Always (structured output) |
--context all |
Need full section |
-C N |
Need N lines before/after |
-A N / -B N |
Asymmetric context |
--max-lines N |
Limit large sections |
Common Pitfalls
- Semantic queries: "Compare X vs Y" won't work. Search
"X"and"Y"separately. - Too broad: "authentication" returns too much. Try
"JWT auth","OAuth flow". - Missing sources: Check
blz listfirst. Add sources withblz add. - One search only: Try multiple query variations.
MCP Alternative
For structured operations, MCP tools are also available:
// Search documentation
mcp__blz__blz_find({ query: "test runner" })
// Retrieve citations
mcp__blz__blz_find({ snippets: ["bun:304-324"] })
// List available sources
mcp__blz__blz_list_sources()
// Add new source
mcp__blz__blz_add_source({ alias: "react", url: "https://react.dev/llms.txt" })
// Learn blz usage
mcp__blz__blz_learn({})
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.
- 4d ago First seen · 87 lines · 68 tokens per session scan A e09d32a70a92
blz-docs-search is a skill published in the GitHub repository outfitter-dev/blz (27 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 721 once invoked, about $0.0003 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 skills, from other repositories
seller-research
Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.
product-research
Use when researching or comparing a specific product, model, or variant for a buying decision, especially when specifications conflict, fit or compatibility matters, retailer copy dominates, or the evidence may be incomplete.
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
skills
Your next session starts cold. No memory of what you built, what broke, what you decided. Every memory you write is a gift to that future session. The richer the memory, the less time re-learning.
rust-modern-style
Apply rag-rat's Rust style when writing or reviewing Rust: current stable idioms, module-qualified free functions and constants, explicit persistence contracts, and narrow APIs.