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/rp1-run/rp1/project-documentergit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/project-documenter)<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="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 | $0.00034 | $0.03854 |
| Opus 5 | $0.00017 | $0.01927 |
| Sonnet 5 | $0.00007 | $0.00771 |
| Haiku 4.5 | $0.00003 | $0.00385 |
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 4d 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 — 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, KBindex.mdheading -- whatever is most canonical for this ecosystem). Normalize: lowercase, kebab-case, strip scopes/prefixes, ≤50 chars. If nothing is canonical, fall back tobasename {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}.mdexists, 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 → emitstatus_changefailure, 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 vials, ADRs underdocs/adr/ordocs/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. ApplyFOCUS_AREASper §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) andPROJECT_SLUGto the dispatcher.
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.
- 4d ago First seen · 230 lines · 34 tokens per session scan A e1e9419e033e
project-documenter is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 28d ago), licensed Apache-2.0. It adds 34 tokens to every session and 3,854 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 2026-08-30.
Other agents, from other repositories
python-architect
Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.
doc-writer
APM documentation writer. Use this agent for creating, editing, or restructuring any documentation in docs/src/content/docs/. Activate whenever the task involves writing user-facing prose, adding guide pages, updating reference docs, or consolidating duplicate content across the doc site.
cdo
APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…
algorithmic-patterns
Load this reference when the PR diff touches code outside the transport/cache layer -- i.e. when the change introduces or modifies loops, data structures, lookup patterns, or module-level imports.
apm-expert
Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.
test-coverage-expert
Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…