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 skills/precisionutilityguild/docforge/docforgenpx skills add PrecisionUtilityGuild/docforge --skill docforgegit clone --depth 1 https://github.com/PrecisionUtilityGuild/docforgeWhat 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 | $0.00025 | $0.00656 |
| Opus 5 | $0.00013 | $0.00328 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
docforge 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocForge Agent Skill
Rules
- Never generate raw Typst unless the user explicitly requests advanced mode.
- Always follow:
docforge_list_templates→docforge_get_template_schema→docforge_create_document. - Treat JSON data as the contract; validate against schema before calling create.
- Use LaTeX only for math fragments in designated schema fields (
equations[].latexin research_report). - Always
docforge_preview_documentbefore final delivery. - Always
docforge_lint_documentbeforedocforge_export_document. - On compile failure: read
agent_actionandsuggested_repairs, calldocforge_repair_document, then recompile. Do not freestyle Typst fixes. - After compile, call
docforge_visual_qa_documentfor layout issues lint may miss. - Use
docforge_generate_template_scaffold+docforge_register_custom_templatefor custom templates. - When data is incomplete, ask for missing required fields — do not invent summary/risks without labeling assumptions.
Workflow
list_templates → get_template_schema → create_document → compile_document
→ repair_document (if suggested_repairs) → compile_document
→ save_document_version (before major edits) → lint_document → preview_document
→ export_document → destroy_document (optional cleanup)
Templates
| Template | Use case |
|---|---|
executive_memo |
Leadership/board memo |
sales_proposal |
Client proposal from discovery |
research_report |
Analytical report with citations appendix |
incident_report |
Post-incident from transcript |
kpi_report |
Board KPI update from CSV + notes |
postmortem |
Blameless incident review |
project_status |
Weekly status with RAG indicators |
decision_record |
ADR-style decision documentation |
meeting_brief |
Pre-meeting context doc |
invoice |
Line-item invoice with computed totals |
contract_summary |
Contract clause summary |
MCP resources
docforge://templates— catalog (built-in + marketplace)docforge://marketplace— community templates onlydocforge://templates/{id}/readme— agent READMEdocforge://templates/{id}/sample— sample JSON
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 · 67 lines · 25 tokens per session scan A 3803af35c114
docforge is a skill published in the GitHub repository PrecisionUtilityGuild/docforge (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 656 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 skills, from other repositories
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
prfaq
This skill should be used when the user asks to "write a PR/FAQ", "prfaq", "working backwards", "product discovery", "evaluate a product idea", "press release FAQ", "test product value", "revise prfaq", "update prfaq", "add research to prfaq", "add FAQs", "run a meeting", "review meeting", "hive meeting", "autonomous…
docuqueue
Generate PDFs, fill forms, and manage documents using DocuQueue. Use when the user asks to "create a PDF", "generate a document", "fill a form", "make an invoice", "create a contract", "build a certificate", "create a proposal", or mentions DocuQueue, document generation, PDF creation, or form filling. Not for…
predict-intelligence
Predict intelligence skill for AI agents. Generates professional PDF reports with probability-ranked predictions, D3 visualizations, and Polymarket consensus signals. Covers geopolitics, finance, tech, elections, and any predicting question. Use when user asks about event predictions, probability predicts, "when will…
beautiful-pdf-mcp
You are an editor-typesetter. Your job is to produce PDFs that look professionally designed, not machine-generated. That means: correct fonts, correct spacing, correct page rhythm.
docuqueue
Skill "docuqueue" from docuqueue/docuqueue-mcp, covering docuqueue document generation, available mcp tools, workflow, example prompts and constraints.