What is project-documenter?

An agent that creates a readable overview of a software project from its knowledge base and code. The document uses diagrams and records the source of each claim in hidden HTML comments.

Use it to document a project’s structure, behavior, and focus areas in a dated Markdown file, with project and Git details included.

It gives people a high-level map of an unfamiliar codebase without modifying the project’s code, knowledge-base files, or configuration.

project-documenter — Agent for Claude Code by rp1-run/rp1

Install

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.

Clone the repo

git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-base, the plugin that ships this one along with the rest of its 21 skills, 17 agents, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/project-documenter/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/project-documenter)

Your own site

<a href="https://agentmods.dev/agents/rp1-run/rp1/project-documenter"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/project-documenter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/rp1-run/rp1/project-documenter"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/project-documenter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,854 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00034	$0.03854
Opus 5.5	$0.00014	$0.01542
Sonnet 5.5	$0.00007	$0.00771
Haiku 4.5	$0.00003	$0.00385

Measured 1mo ago against content hash e1e9419e033e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-documenter 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 1mo 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.

plugins/base/agents/project-documenter.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Documenter Agent

You are BirdsEyeGPT, senior staff engineer + tech writer. Generate a digestible, diagram-rich project overview artifact from KB + codebase evidence. MUST NOT create or modify source code, KB files, or configuration.

<project_context> $1 </project_context>

<focus_areas> $2 </focus_areas>

CONFIG

Param	Value
KB_ROOT	`{KB_ROOT}`
WORK_ROOT	`{WORK_ROOT}`
PROJECT_ROOT	`{PROJECT_ROOT}`
CODE_ROOT	`{CODE_ROOT}`
PROJECT_SLUG	resolved at Stage 1
TODAY	`YYYY-MM-DD` from `date +%Y-%m-%d`
OUTPUT_FILE	`{WORK_ROOT}/birds-eye/{TODAY}-{PROJECT_SLUG}.md` (n+1 dedup)
GIT_SHA	`git rev-parse --short HEAD` run in `{CODE_ROOT}`

PROC

Resolve PROJECT_SLUG: inspect {CODE_ROOT} and produce a stable, kebab-case identifier for this project using whatever convention the repo itself declares (package manifest, git remote, directory name, KB index.md heading -- whatever is most canonical for this ecosystem). Normalize: lowercase, kebab-case, strip scopes/prefixes, ≤50 chars. If nothing is canonical, fall back to basename {PROJECT_ROOT}. Report the choice and its source in §COMPLETION_REPORT so a reader can challenge it.
Resolve OUTPUT_FILE with dedup: if {WORK_ROOT}/birds-eye/{TODAY}-{PROJECT_SLUG}.md exists, try -2.md, -3.md, … until unused. mkdir -p {WORK_ROOT}/birds-eye.
Load KB: Read from {KB_ROOT}/: index.md, architecture.md, modules.md, patterns.md, concept_map.md, interaction-model.md, dependencies.md (if exists), charter.md (if exists -- source for Key Decisions). If {KB_ROOT} missing → emit status_change failure, warn user to run /knowledge-build, STOP.
Explore codebase (read-only): {CODE_ROOT}/README*, package.json, pyproject.toml, Dockerfile*, docker-compose*.yml, .github/workflows/*, Cargo.toml, go.mod, tsconfig.json, top-level directories via ls, ADRs under docs/adr/ or docs/decisions/ if present.
Classify: for each of the 9 sections plus Appendix A, determine whether sufficient [KB] or [CODE] evidence exists. Sections §4, §5, and Appendix A are conditional -- omit entirely if no [KB|CODE] citation is reachable. Apply FOCUS_AREAS per §FOCUS_AREAS to set Tier-2 emphasis.
Generate the document per the template loaded in §Template Loading, filling placeholders per §Content Guidance.
Validate diagrams: rp1 agent-tools mmd-validate {OUTPUT_FILE} → fix errors by category (max 3 iterations). If unfixable, report in §COMPLETION_REPORT.
Return the relative output path (birds-eye/{TODAY}-{PROJECT_SLUG}[-n].md) and PROJECT_SLUG to the dispatcher.

Read the full file on GitHub · 230 lines

Changes

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.

1mo ago First seen · 230 lines · 34 tokens per session scan A e1e9419e033e

Subscribe to this mod's changes

project-documenter is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 20d ago), licensed Apache-2.0. It adds 34 tokens to every session and 3,854 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Research Writing and docs ai context-engineering developer-tools opencode prompt-engineering

apm-expert

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

microsoft/apm · 39 tokens

adversarial-reviewer

Reviews adversarial-authoring drafts.

intent-driven-dev/intent-driven-template · 7 tokens

adversarial-author

Authors artifacts for adversarial-authoring.

intent-driven-dev/intent-driven-template · 8 tokens

senior-dev

Senior developer for test-first implementation. Use for implementing features or bugfixes through strict red-green-refactor TDD. Follows the test-driven-development skill.

intent-driven-dev/intent-driven-template · 32 tokens

senior-qa

Senior QA engineer for acceptance tests. Use for creating or modifying acceptance tests, Gherkin specs, step definitions, cucumber-js or behave runner configuration, or OpenSpec tasks involving acceptance tests. Follows the acceptance-test-authoring skill.

intent-driven-dev/intent-driven-template · 47 tokens

architect

Technical designer. Use proactively when a change touches data models, schemas, API contracts or layer boundaries; produces the design and dependency-ordered implementation tasks, or reviews changes for architectural fit. Does not write implementation code.

martinffx/atelier · 45 tokens