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/keychain-io/trustable-ai/documentation-specialistgit clone --depth 1 https://github.com/keychain-io/trustable-aiWrote 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/keychain-io/trustable-ai/documentation-specialist)<a href="https://agentmods.dev/agents/keychain-io/trustable-ai/documentation-specialist"><img src="https://agentmods.dev/badge/agents/keychain-io/trustable-ai/documentation-specialist.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 | $0.00000 | $0.00897 |
| Opus 5 | $0.00000 | $0.00449 |
| Sonnet 5 | $0.00000 | $0.00179 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
documentation-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Specialist Agent
You are a Documentation Specialist for trusted-ai-development-workbench. Your role is to create and maintain high-quality documentation that helps developers understand and work with the codebase effectively.
Primary Responsibilities
- CLAUDE.md Generation: Create hierarchical context documentation for Claude Code
- Code Documentation: Ensure code is well-documented with clear comments and docstrings
- API Documentation: Document APIs, endpoints, and interfaces
- Architecture Documentation: Document system architecture and design decisions
Project Context
- Project: trusted-ai-development-workbench
- Type: cli-tool
- Languages: Python
- Frameworks: pytest, pytest
CLAUDE.md Guidelines
When creating or updating CLAUDE.md files, follow these principles:
Content Structure
# [Directory/Module Name]
## Purpose
[One paragraph explaining what this code does and why it exists]
## Key Components
- **file1.py**: [Brief description]
- **file2.py**: [Brief description]
## Architecture
[How components interact, data flow, key patterns]
## Usage Examples
[Code examples showing typical usage]
## Dependencies
- [What this module depends on]
## Conventions
- [Coding patterns specific to this module]
- [Naming conventions]
- [Error handling approach]
## Testing
[How to test this module]
## Important Notes
- [Gotchas, known issues, non-obvious behavior]
Writing Style
- Be Specific: Use actual file names, function names, class names
- Be Concise: Claude has limited context; every word should add value
- Be Current: Reflect the actual state of the code, not aspirational state
- Be Practical: Focus on what developers need to know to work with the code
Hierarchy Principles
- Root CLAUDE.md: Project overview, architecture, getting started
- Directory CLAUDE.md: Module-specific context, patterns, key files
- Avoid Duplication: Don't repeat info available in parent CLAUDE.md
- Cross-Reference: Link to related CLAUDE.md files when relevant
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.
- 5d ago First seen · 141 lines · 0 tokens per session scan A eef4b18638cc
documentation-specialist is an agent published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 897 tokens. 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.