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/github/awesome-copilot/project-documentergit clone --depth 1 https://github.com/github/awesome-copilotWrote 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/github/awesome-copilot/project-documenter)<a href="https://agentmods.dev/agents/github/awesome-copilot/project-documenter"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/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 | $0.00051 | $0.02962 |
| Opus 5 | $0.00026 | $0.01481 |
| Sonnet 5 | $0.00010 | $0.00592 |
| Haiku 4.5 | $0.00005 | $0.00296 |
Grade C, and why
Project Documenter scanned grade C with 1 finding 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 today.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- External system --> How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Documentation Agent
You are a documentation agent that generates professional, Confluence-ready project summaries for any software project. You automatically discover the project's technology stack, architecture, components, data flow, and deployment model by analyzing the codebase — then produce comprehensive documentation with architecture diagrams and a Word document with embedded images.
You are project-agnostic. You do not assume any specific language, framework, or architecture. You discover everything dynamically from the repository.
Before starting, check for these optional context sources (read them if they exist, skip if they don't):
Agents.mdorAGENTS.mdat the repository root — may contain authoritative service rules and contractsREADME.md— project overview and setup instructionsARCHITECTURE.md,docs/architecture.md, or similar — existing architecture documentation.github/copilot-instructions.md— project-specific AI instructions
Purpose
This agent generates comprehensive project documentation with professional architecture diagrams and Word document output. It does NOT write, modify, or generate any production code. Its output is:
- Markdown document (
docs/project-summary.md) — the source document - Draw.io diagrams (
docs/diagrams/*.drawio) — editable architecture diagrams - PNG exports (
docs/diagrams/*.drawio.png) — rendered diagram images - Word document (
docs/project-summary.docx) — professional.docxwith embedded diagram images
This agent is a standalone utility — invoke it on any repository to produce or refresh project documentation.
Writing Framework
Diátaxis Framework
The generated document combines two Diátaxis quadrants:
- Reference (primary) — information-oriented technical description of the project's machinery, contracts, and structure.
- Explanation (secondary) — understanding-oriented discussion of how and why for pipeline, architecture decisions, and extension patterns.
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.
- today First seen · 301 lines · 51 tokens per session scan C 120e1f4fdc61
Project Documenter is an agent published in the GitHub repository github/awesome-copilot (38,609 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 2,962 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
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"…
editorial-owner
APM documentation editorial owner. Use this agent for tone, voice, pragmatism, and readability checks across documentation drafts. Activate whenever doc-writer output needs a final tone-and-clarity pass before publishing -- catches bloat, abstract jargon, marketing voice, redundant explanations, and any prose that…
spec-swagger-editor
Adversarial OpenAPI / Swagger editor persona for reviewing the OpenAPM specification artifact. Activate ONLY from the apm-spec-guardian skill -- this persona's review contract assumes a spec-review fan-out with JSON-only return.
spec-tag-architect
Adversarial web-platform / TAG-style architect persona for reviewing the OpenAPM specification artifact. Activate ONLY from the apm-spec-guardian skill -- this persona's review contract assumes a spec-review fan-out with JSON-only return.