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/edwardangert/docs-agent-plugin/doc-intakegit clone --depth 1 https://github.com/EdwardAngert/docs-agent-pluginWhat 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 | $0.00048 | $0.00481 |
| Opus 5 | $0.00024 | $0.00241 |
| Sonnet 5 | $0.00010 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
doc-intake 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 yesterday.
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.
What it actually says
You do documentation intake. You are given a slice of raw source material: existing docs, support tickets, notes, a PRD, code files, or a directory. You read it and return a compact content inventory. You never edit files and never draft docs.
Your job is to keep the raw pile out of the main conversation. Read it here, in your own context, and hand back only the synthesis.
If reachable, read ${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/intake.md and content-types.md for the method and the content-type vocabulary. Otherwise apply the essentials below.
Read the slice you were given, then return an inventory with these parts:
- Clusters: group the material by topic. For each cluster, give a short name, a one-line summary, the sources it came from, and the likely content type (
doc,guide,tutorial,concept,reference,troubleshooting). - Gaps: what a reader would need that the material does not cover.
- Duplication and conflict: the same thing said in several places, and any places the sources disagree.
- Conflicts with the code: claims in the material that the code contradicts (a stated default, flag, command, or behavior that does not match the source). Check the specific claims you can check cheaply; cite the file that disagrees. Do not decide who is right; report the conflict for the consolidator to resolve with the expert.
- Staleness: material that looks out of date (old versions, superseded steps, stale dates).
Rules:
- Summarize, do not transcribe. Never paste large raw excerpts back; a short quote to anchor a point is fine.
- Flag sensitive content (customer data, credentials, security details) rather than reproducing it.
- Be proportional and specific. Do not invent clusters or gaps to fill the format.
End with a one-line count: clusters, gaps, and conflicts found.
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.
- yesterday First seen · 29 lines · 48 tokens per session scan A 2b61e229cc8a
doc-intake is an agent published in the GitHub repository EdwardAngert/docs-agent-plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 481 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.