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 skills add nemock/company-brain --skill doc-generategit clone --depth 1 https://github.com/nemock/company-brainWrote 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/skills/nemock/company-brain/doc-generate)<a href="https://agentmods.dev/skills/nemock/company-brain/doc-generate"><img src="https://agentmods.dev/badge/skills/nemock/company-brain/doc-generate.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 5.1 | $0.00154 | $0.02688 |
| Opus 5 | $0.00077 | $0.01344 |
| Sonnet 5 | $0.00031 | $0.00538 |
| Haiku 4.5 | $0.00015 | $0.00269 |
Grade A, and why
doc-generate 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 8d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
doc-generate
This skill turns the typed vault into planning documents. The vault is the source of truth; the documents are derived artifacts you can regenerate any time and that get committed under <vault>/exports/.
You do not write document content by hand. The generators read the schema, pull the right typed nodes, and emit consistent, profile-aware output. Your job is to invoke the right cb render command and surface any issues to the user.
Before any render
- Confirm the vault path. Default: current working directory. Refuse politely if there is no
_system/PROFILE.md— that's the marker of a vault. - Run
cb validate --path <vault>first. A vault with errors will still render, but uncited claims and broken edges will surface in the output. If validate reports errors, tell the user and offer to fix them viaintakeoratomizebefore generating. - Confirm the active profile. Run
cb describe-profile --path <vault>to know whether medical-device-only sections will appear. The profile decides which sections render.
What ships today (21 generators)
Full implementations (v0.3.0)
| Document | Markdown | HTML | DOCX | Profile |
|---|---|---|---|---|
| Marketing Requirements Document (MRD) | ✅ | ✅ | ✅ | all |
| One-pager | ✅ | ✅ | — | all |
Scaffolds (v0.4.0)
Runnable templates that query the right typed nodes, fill in what they can, and flag the output as a scaffold in the footer. Adopters fill in the placeholders by hand. Full per-doc implementations land in v1.x.
| Document | CLI name | Profile | Length norm |
|---|---|---|---|
| PID (Project Initiation Document) | pid |
all | 2–4 pages |
| Project charter | project-charter |
all | 1 page |
| Stakeholder register | stakeholder-register |
all | 1–2 pages (table) |
| Risk register (planning) | risk-register |
medical-device | 1–3 pages |
| Status report | status-report |
all | 1 page |
| Meeting minutes | meeting-minutes |
all | 1 page (not 12) |
| Lessons learned / close-out | lessons-learned |
all | 1–2 pages |
| Business plan | business-plan |
all | 8–15 pages |
| Sales battle card (per competitor) | sales-battle-card |
all | 1–2 pages |
| Competitive brief | competitive-brief |
all | 3–5 pages |
| IFU comparison report | ifu-comparison |
medical-device | 2–4 pages |
| Decision log / ADR roll-up | decision-log |
all | 1–10 pages |
| Press release / launch | press-release |
all | 1 page |
| Investor update | investor-update |
all | 1–2 pages |
| Onboarding doc | onboarding-doc |
all | 3–6 pages |
| System Requirements Document (SRD) | srd |
all | 5–15 pages |
| Software Requirements Specification (SRS) | srs |
all | 5–20 pages |
| Hardware Requirements Specification (HRS) | hrs |
all | 5–20 pages |
| Risk brainstorm | risk-brainstorm |
medical-device | 2–4 pages |
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.
- 8d ago First seen · 161 lines · 0 tokens per session scan A 5e7d04a2032a
doc-generate is a skill published in the GitHub repository nemock/company-brain (5 stars, last pushed 3mo ago), licensed MIT. It adds 154 tokens to every session and 2,688 once invoked, about $0.0008 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
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
extract-memory
Extract writing style, personality traits, and key insights from a collection of documents (Markdown, PDF, TXT, DOCX) and save them as a Claude Code memory file. Use when the user wants to capture their writing DNA, build a personal style guide, or create a reusable memory profile from their existing content.
convert-lakebook
Convert Yuque .lakebook exports to Markdown files. Use when the user has a .lakebook file and wants to extract all documents as individual .md files. Supports batch conversion with an auto-generated index file.
query
Interactive knowledge assistant via Telegram. Can read, create, and modify documents. Destructive actions require user approval.
summarizer
A document-reading agent that produces structured summaries, with core points, key facts, possible connections, and source references.
resume-tuning
An interactive tool for creating and improving PDF résumés from existing files or spoken or written career details. It can tailor a résumé to a job description and check whether it is readable by applicant-screening software.