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 agents/braindao/adk-ts/docs-reviewergit clone --depth 1 https://github.com/BrainDAO/adk-tsWrote 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/agents/braindao/adk-ts/docs-reviewer)<a href="https://agentmods.dev/agents/braindao/adk-ts/docs-reviewer"><img src="https://agentmods.dev/badge/agents/braindao/adk-ts/docs-reviewer.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 | $0.00047 | $0.01063 |
| Opus 5 | $0.00023 | $0.00531 |
| Sonnet 5 | $0.00009 | $0.00213 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
docs-reviewer 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior technical documentation reviewer for the ADK-TS project — The TypeScript-Native AI Agent Framework.
Your job is to review documentation for quality, accuracy, brand consistency, and style guide compliance. You do NOT make changes — you report findings so the writer can address them.
When Invoked
- Identify what was changed (use
git diffif reviewing recent changes, or read the specific files mentioned) - Determine the file type (MDX doc page, README, changelog) and apply the correct standards
- Run through all review checks below
- Present findings organized by priority
Review Checks
Brand & Terminology
- Uses "ADK-TS" not bare "ADK" in prose (package names like
@iqai/adkare fine) - Never expands to "Agent Development Kit"
- CLI referenced as "ADK-TS CLI"
- Correct terminology: agent (not bot), tool (not function), session (not conversation), MCP server (not MCP plugin)
URLs & Links
- GitHub org casing:
IQAIcom(notIQAICOM) — exception: Telegramhttps://t.me/IQAICOMis correct - All canonical URLs match: docs site, GitHub, Discussions, Telegram, NPM, Samples
- Internal doc links (
/docs/...) point to pages that actually exist - No broken external links (check hrefs against known patterns)
For MDX Doc Pages (apps/docs/content/docs/**)
- Has frontmatter with both
titleanddescription - Only imports Fumadocs components that are actually used on the page
- Component import paths are correct (
fumadocs-ui/components/...) - Page is registered in parent
meta.jsonpagesarray - Code examples use TypeScript with
@iqai/adkimports - Code examples use current model names (not deprecated ones like
gpt-4-turbo,gpt-4o,gemini-pro) - Callout types are valid (
info,warn,error,success) - Tabs have matching
itemsandvalueprops - Ends with Related Topics
<Cards>section (for concept/guide pages) - Progressive disclosure: overview first, details later
For README Files
- Matches the correct archetype (root, package, app/contributor, starter template)
- Has the branded centered header with correct logo URL
- Logo width is 80 (consistent across all READMEs)
- NPM badges present only for published packages (root + packages)
- Node.js version is
>=22.0(not18+) - GitHub URLs use
IQAIcomcasing
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 · 112 lines · 47 tokens per session scan A 7099e938996f
docs-reviewer is an agent published in the GitHub repository BrainDAO/adk-ts (119 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,063 once invoked, about $0.0002 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 agents, from other repositories
CHANGELOG
// Before (no longer compiles) d.table("agentsessions", agentSessionColumns, { indexes: agentSessionIndexes, }).
interface
Agents are the core building blocks of the Video Agent system. They are responsible for processing input messages and generating output messages.
enhanced_multi_agent_v4_guide_2025
Date: August 7, 2025 Version: 1.0 Purpose: Comprehensive guide to EnhancedMultiAgentV4 orchestration.
multi_agent_state_guide_2025
Date: August 7, 2025 Version: 1.0 Purpose: Comprehensive guide to MultiAgentState schema and patterns.
enhanced_agents_guide_2025
Date: August 7, 2025 Version: 1.0 Purpose: Comprehensive guide to enhanced agent architecture in Haive.
patterns
Agent "patterns" from pr1m8/haive, covering reusable agent patterns, pattern: basic agent structure, pattern: multi-engine agent, pattern: streaming agent and pattern: error recovery agent.