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/archubbuck/workspace-architect/project-documentergit clone --depth 1 https://github.com/archubbuck/workspace-architectWrote 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/archubbuck/workspace-architect/project-documenter)<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/project-documenter"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/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 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.
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 --> This is a copy
100% identical to Project Documenter — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
- yesterday First seen · 301 lines · 51 tokens per session scan C 120e1f4fdc61
Project Documenter is an agent published in the GitHub repository archubbuck/workspace-architect (18 stars, last pushed yesterday), licensed ISC. 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). It is 100% identical to Project Documenter, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
office-assistant
Office assistant agent – generate and edit PowerPoint (.pptx via python-pptx), Excel (.xlsx via openpyxl), Word (.docx via python-docx), PDF (.pdf via reportlab), and web-based slide decks (self-contained reveal.js HTML); outputs auto-delivered via codeexecutor OUTPUTDIR as /api/media/ attachments.
claim-checker
Sub-agent that audits a specific claim against the PDF cited. Invoked by citation-receipts skill for deep PDF↔claim verification. Returns structured verdict (VALID/ADJUST/INVALID/UNVERIFIABLE) with evidence quoted from the source. Isolates the heavy PDF reading from the main agent's context.
knowledge-extractor
Coordinator agent that routes content to specialized sub-agents and produces structured knowledge artifacts (literature notes, atomic zettels, action items). Takes any content type — URL, PDF, conversation export, local file, or raw text.
page1-validator
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
pdf-extractor
Sub-agent that extracts structured text from PDF files. Preserves document structure, handles tables, and detects OCR needs. Returns structured markdown with metadata.
cascade-runner
Sub-agent that orchestrates the PDF acquisition cascade for a batch of refs. Delegates the actual work to the worker B CLI but tracks progress and aggregates results across the batch. Invoke from sota-writer or pdf-cascade skill when handling N > 5 refs in one shot.