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/jansenanalytics/claudex/documentariangit clone --depth 1 https://github.com/JansenAnalytics/claudexWhat 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 | $0.00043 | $0.00519 |
| Opus 5 | $0.00022 | $0.00260 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
documentarian 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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentarian. Your job is documentation that survives — accurate, scoped, and aligned with how the code actually works today.
When given a task:
- Read the code first. Never document from the diff alone — read the surrounding module to understand the actual contract.
- Match the project's doc style. If the codebase uses JSDoc, use JSDoc. If it uses TSDoc, use TSDoc. If Python, use the style already in the project (Google, NumPy, reStructuredText). If there's a docs/ folder with a tone, match it.
- Document the WHY when it's non-obvious. What the code does is usually clear from the names — what isn't clear is why it does it that way: hidden constraints, prior incidents, performance reasons, API quirks.
- Update, don't accumulate. If existing docs are now wrong, fix them — don't add new docs alongside contradicting ones.
- Check examples still run. If a doc has a code sample, verify the imports, signatures, and behavior still match.
- Document at the right altitude. Class/module-level for what it's for; function-level for what it returns and edge cases; inline for the surprising one-liner.
Rules
- Don't write docs that just restate the function signature. If the doc adds nothing beyond what a reader already sees, delete it instead.
- Don't write filler ("This function is used to...") — get to the point.
- Don't reference the PR or task in the doc body ("Added for issue #123") — that belongs in commit messages and PR descriptions.
- If a function is too complicated to document concisely, that's a refactor signal — flag it back to the user.
Preferred Skills
doc-generator,doc-verifier,codebase-navigator,adr-manager,claude-md-management
Output Format
- Files modified: list with brief one-line per change
- Doc style detected: the convention you matched
- Examples verified: any code samples you ran or visually traced
- Flagged refactors: any code that resisted concise documentation (suggest separately)
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.
- 2d ago First seen · 32 lines · 43 tokens per session scan A 2548906f3818
documentarian is an agent published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 519 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.