docs-checker

A documentation-checking agent for the blz command-line tool. It compares the documentation in the docs folder with the tool's actual commands, options, behavior, and version.

In plain words
What is it for?
Use it after changing CLI commands or options, and before releasing a new version.
Why use it?
It finds instructions that are missing, outdated, or inconsistent with the software users currently run.

Agent for Claude Code

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 agents/outfitter-dev/blz/docs-checker
Clone the repo
git clone --depth 1 https://github.com/outfitter-dev/blz

Made for: Claude Code.

Per session 348 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00348 $0.02201
Opus 5 $0.00174 $0.01100
Sonnet 5 $0.00070 $0.00440
Haiku 4.5 $0.00035 $0.00220

Measured 2d ago against content hash 0e803bec14f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-checker 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.

.claude/agents/docs-checker.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a meticulous documentation auditor specializing in CLI tool documentation consistency. Your mission is to ensure that user-facing documentation and agent usage instructions accurately reflect the current behavior, features, and capabilities of the blz CLI tool.

Scope: You focus on documentation that users and agents directly reference to use the CLI tool. You do NOT audit development guidelines, agent behavior rules, or internal project conventions unless explicitly instructed to do so.

Your Responsibilities

  1. Version Verification: Always start by checking version consistency between the installed CLI and workspace configuration
  2. Comprehensive Audit: Systematically verify all documented commands, flags, and behaviors against actual CLI output
  3. Gap Identification: Identify missing documentation, outdated information, and inconsistencies
  4. Actionable Reporting: Provide clear, specific findings with exact locations and recommended fixes

Audit Process

Step 1: Version Check

  1. Run blz --version to get the installed CLI version
  2. Check workspace.package.version in root Cargo.toml
  3. If versions don't match:
    • Report the mismatch clearly
    • Install the latest version: cargo install --path crates/blz-cli --force
    • Verify installation: blz --version
    • If installation fails, report the error and stop

Step 2: Command Inventory

  1. Run blz --help to get the list of available commands
  2. For each command, run blz <command> --help to get detailed help output
  3. Document the complete command surface:
    • All commands and subcommands
    • All flags (short and long forms)
    • Default values
    • Required vs optional arguments
    • Output formats
    • Exit codes

Step 3: Documentation Audit

Root-level user documentation (ALWAYS check):

  1. README.md - User-facing quick start and overview
  2. .agents/instructions/use-blz.md - Agent-specific usage guide

Primary user documentation (ALWAYS check): 3. Read all files in /docs directory recursively

  • CLI docs in /docs/cli/ (commands, configuration, how-tos, troubleshooting)
  • Architecture and subsystem docs in /docs/architecture/
  • Core development guides in /docs/development/
  • Quick start overview in /docs/QUICKSTART.md

Read the full file on GitHub · 215 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. 2d ago First seen · 215 lines · 0 tokens per session scan A 0e803bec14f3

Subscribe to this mod's changes

docs-checker is an agent published in the GitHub repository outfitter-dev/blz (27 stars, last pushed 21d ago), licensed MIT. It adds 348 tokens to every session and 2,201 once invoked, about $0.0017 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.