blz-source-management

blz-source-management is a skill for Claude Code, Codex from outfitter-dev/blz. It costs 70 tokens per session (812 once invoked), scanned A, original, MIT.

A guide for adding and maintaining documentation sources in the blz command-line tool. It focuses on llms.txt files, which are web pages formatted for AI-readable documentation.

In plain words
What is it for?
Use it when discovering llms.txt or llms-full.txt files, checking them with a dry run, adding them to blz, refreshing content, or verifying the documentation index.
Why use it?
It helps you find the right documentation URL, check whether it contains complete documentation or only links, and avoid adding unusable sources to blz.

Skill for Claude CodeCodex

Part of the blz plugin — 2 skills, 10 commands, 7 agents, 1 hook, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/outfitter-dev/blz/blz-source-management
Any agent
npx skills add outfitter-dev/blz --skill blz-source-management
Clone the repo
git clone --depth 1 https://github.com/outfitter-dev/blz

Made for: Claude Code, Codex.

Or install blz, the plugin that ships this one along with the rest of its 2 skills, 10 commands, 7 agents, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for blz-source-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/outfitter-dev/blz/blz-source-management.svg)](https://agentmods.dev/skills/outfitter-dev/blz/blz-source-management)
Your own site
<a href="https://agentmods.dev/skills/outfitter-dev/blz/blz-source-management"><img src="https://agentmods.dev/badge/skills/outfitter-dev/blz/blz-source-management.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.00812
Opus 5 $0.00035 $0.00406
Sonnet 5 $0.00014 $0.00162
Haiku 4.5 $0.00007 $0.00081

Measured 4d ago against content hash 9e930b19653b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blz-source-management scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s <index-url> | head -50
packages/agents/skills/blz-source-management/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BLZ Source Management

Add and manage llms.txt documentation sources for local search.

Source Types

Type Description Action
llms-full.txt Complete documentation (preferred) Add directly
llms.txt (full) Complete docs under standard name Add directly
llms.txt (index) Links to other docs (< 100 lines) Expand linked files

Adding Sources

Standard Workflow

# 1. Dry-run to validate
blz add react https://react.dev/llms.txt --dry-run --quiet

# 2. Check output
# Good: contentType: "full", lineCount > 1000
# Index: contentType: "index", lineCount < 100 → find linked docs

# 3. Add if good
blz add react https://react.dev/llms.txt -y

# 4. Verify
blz list --json | jq '.[] | select(.alias=="react")'

Discovering URLs

Web search patterns:

"llms-full.txt" site:docs.example.com
"llms.txt" OR "llms-full.txt" <library-name>
site:github.com/org/repo "llms.txt"

Common URL patterns:

https://docs.example.com/llms-full.txt
https://example.com/llms.txt
https://example.com/llms-full.txt

Index File Handling

If dry-run shows contentType: "index" with < 100 lines:

# Inspect the index
curl -s <index-url> | head -50

# Look for .txt references like:
# ./guides.txt
# ./js.txt
# ./python.txt

# Resolve and add each linked file
blz add supabase-guides https://supabase.com/llms/guides.txt -y
blz add supabase-js https://supabase.com/llms/js.txt -y

Quality Criteria

Criteria Good Index Skip
contentType "full" "index" "unknown"
lineCount > 1000 < 100 < 50
Action Add Expand Investigate

Alias Best Practices

Good aliases:

  • bun, react, deno (short, clear)
  • supabase-guides (variant-specific)
  • langchain-python (language-specific)

Bad aliases:

  • b (too short)
  • my-docs (vague)
  • the-react-docs-2024 (too long)

Management Commands

# List sources
blz list --json
blz list --status --json    # With freshness

# Refresh sources
blz refresh --all --json    # Update all
blz refresh bun --json      # Update specific

# Remove source
blz remove bun

# Source details
blz info bun --json

Read the full file on GitHub · 117 lines

Changes

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.

  1. 4d ago First seen · 117 lines · 70 tokens per session scan A 9e930b19653b

Subscribe to this mod's changes

blz-source-management is a skill published in the GitHub repository outfitter-dev/blz (27 stars, last pushed 23d ago), licensed MIT. It adds 70 tokens to every session and 812 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

cinderline/northcinder · 46 tokens

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.

cinderline/northcinder · 43 tokens

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.

stevelr/anytype · 46 tokens

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.

zycaskevin/Vault-Agent-Memory · 46 tokens

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.

jackccrawford/Geniuz · 0 tokens

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.

cq27-dev/rag-rat · 37 tokens