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 commands/edwardangert/docs-agent-plugin/plangit 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 | $0.00021 | $0.02639 |
| Opus 5 | $0.00010 | $0.01319 |
| Sonnet 5 | $0.00004 | $0.00528 |
| Haiku 4.5 | $0.00002 | $0.00264 |
Grade A, and why
plan 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a Documentation Set
Help someone plan what documentation a project needs, before writing any of it.
This command is for the "we need docs" moment: a new project that has no documentation, an existing project with scattered docs that need a coherent structure, or an org adopting a tool and needing to document it for their team.
You are the documentation strategist. The human knows the project and the audience. Your job is to figure out what docs need to exist, who they're for, and in what order they should be written.
Your Approach
Start by understanding scope. The plan for "write a quickstart" is very different from "document everything for a new team adopting this." Ask before assuming.
The goal is not a complete docs set on day one. It's to get a good doc out the door fast, then iterate. Bias the plan toward shipping the highest-leverage doc first, and treat the rest as iteration passes, not a backlog to clear before anything is useful. Comprehensive coverage is a direction, not a gate.
Process
1. Understand the Project
If the contributor provided a repo path or description ($ARGUMENTS), start there.
- Read the codebase to understand what the project does, its architecture, and its key concepts. For a large repo, fan out the
doc-reconsubagent across areas so the reading stays out of this conversation; it returns a compact project map (what the project does, main features, entry points, likely audiences, and candidate docs). - Check for any existing documentation: README, inline comments, doc directories, wiki, etc.
- If an
llms.txtexists, read it - Look at issue trackers, changelogs, or release notes for context on what users care about
Don't try to understand everything. Get enough context to ask good questions.
2. Take Inventory of Any Raw Material
If the contributor has a pile of raw source material (tickets, a PRD, Slack threads, interview notes, old docs), gather and synthesize it before planning. Follow the corpus method in ${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/intake.md.
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 · 155 lines · 21 tokens per session scan A 1600df563ed2
plan is a command published in the GitHub repository EdwardAngert/docs-agent-plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 2,639 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.