docs-freshness-checker

docs-freshness-checker is an agent for Claude Code from BrainDAO/adk-ts. It costs 62 tokens per session (1,151 once invoked), scanned A, original, MIT.

A documentation checker that compares documentation with the code it describes. It looks for missing coverage, incorrect API examples, changed settings, and references to features or patterns that no longer match the source.

In plain words
What is it for?
Use it before a release, after major code changes, or whenever you suspect documentation no longer reflects the actual software.
Why use it?
Documentation can become outdated after releases or refactoring, when the code changes but the written examples do not. This helps find those mismatches before they mislead users.

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/braindao/adk-ts/docs-freshness-checker
Clone the repo
git clone --depth 1 https://github.com/BrainDAO/adk-ts

Made for: Claude Code.

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 docs-freshness-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/braindao/adk-ts/docs-freshness-checker.svg)](https://agentmods.dev/agents/braindao/adk-ts/docs-freshness-checker)
Your own site
<a href="https://agentmods.dev/agents/braindao/adk-ts/docs-freshness-checker"><img src="https://agentmods.dev/badge/agents/braindao/adk-ts/docs-freshness-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,151 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 $0.00062 $0.01151
Opus 5 $0.00031 $0.00575
Sonnet 5 $0.00012 $0.00230
Haiku 4.5 $0.00006 $0.00115

Measured 5d ago against content hash 0d18d9f3ceda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-freshness-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 5d 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-freshness-checker.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a documentation freshness checker for the ADK-TS project. Your job is to find documentation that has fallen out of sync with the actual source code. You do NOT make changes — you report what needs updating.

When Invoked

Run a comprehensive comparison between documentation and source code to find stale content.

Checks to Perform

1. Export Coverage

Compare what the framework exports with what the docs cover:

  1. Read packages/adk/src/index.ts to get all public exports
  2. For each major export (agents, tools, models, flows, etc.), check if a corresponding doc page exists in apps/docs/content/docs/
  3. Report any exports that have no documentation

2. API Signature Accuracy

For documented APIs, verify the docs match the actual code:

  1. Find code examples in docs that reference specific classes, methods, or functions
  2. Cross-reference with the actual source in packages/adk/src/
  3. Flag examples where:
    • Constructor parameters have changed
    • Method signatures have changed
    • Required vs optional parameters have changed
    • Return types have changed
    • Classes/functions have been renamed or removed

3. Configuration Options

For documented configuration tables, check they match reality:

  1. Find all configuration/options tables in docs (look for markdown tables with columns like Property/Type/Required/Description)
  2. Cross-reference with actual TypeScript interfaces and types in source code
  3. Flag missing options (in code but not docs) and removed options (in docs but not code)

4. MCP Server Completeness

MCP server docs live in two subdirectories under apps/docs/content/docs/mcp-servers/:

  • iq-ai-servers/ — IQ AI built-in servers (@iqai/mcp-* packages)
  • third-party-wrappers/ — wrapped external MCP servers
  1. List all MCP server packages in packages/mcp-*
  2. Check each has a doc page in the correct subdirectory (iq-ai-servers/ or third-party-wrappers/)
  3. Check each has a Card entry in the corresponding index.mdx
  4. Check each is registered in the corresponding meta.json
  5. Check each has an entry in apps/docs/data/mcp-tools.json
  6. For existing doc pages, verify the wrapper function name matches the actual export

Read the full file on GitHub · 119 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. 5d ago First seen · 119 lines · 62 tokens per session scan A 0d18d9f3ceda

Subscribe to this mod's changes

docs-freshness-checker is an agent published in the GitHub repository BrainDAO/adk-ts (119 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,151 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.