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/ntaffzii/skill-agents/project-docs-prepnpx skills add ntaffzii/Skill-Agents --skill project-docs-prepgit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/project-docs-prep)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/project-docs-prep"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/project-docs-prep.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 | $0.00218 | $0.01180 |
| Opus 5 | $0.00109 | $0.00590 |
| Sonnet 5 | $0.00044 | $0.00236 |
| Haiku 4.5 | $0.00022 | $0.00118 |
Grade A, and why
project-docs-prep 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Docs Prep
Turns a short project idea (or an existing incomplete docs folder) into a complete, AI-agent-ready documentation set. Produces two operational layers:
- Spec Layer (
docs/) — describes what to build. Five numbered files:01-project-overview.md02-system-requirements.md03-tech-stack-architecture.md04-system-modeling.md05-ux-ui-design.md
- Operational Layer (repo root) — describes how the agent should work and what design tokens/commands look like:
AGENTS.mdDESIGN.mdCLAUDE.mdREADME.md
These two layers are complementary, not redundant. The spec layer is read once during planning. The operational layer is loaded by the agent every session — keep it concise and omit facts inferable from code.
Templates
This skill ships with skeleton templates in templates/. When generating docs for a new project:
- Read the relevant template from
templates/as your starting structure. - Replace all
{{PLACEHOLDER}}markers with project-specific content. - Delete any sections that don't apply — do NOT leave empty headings.
- Add project-specific sections where the template doesn't cover them.
See references/template-usage-guide.md for detailed instructions on each template.
Workflow
Step 1 — Gather Project Info
If given a short idea (e.g. "Meeting room booking system for 50 users"), do not interrogate field-by-field. Draft reasonable content and mark uncertain items with > ⚠️ TODO:. Only ask clarifying questions when the answer would alter architecture or design direction.
Step 2 — Generate docs/01–05
Create numbered specs in docs/. Use the templates in templates/docs/ as starting structure. Maintain consistent section headings. Fill placeholders with project specifics. Keep descriptions clear and accessible for both human developers and AI agents.
Step 3 — Generate AGENTS.md
Use templates/AGENTS.md as base. Include build, test, and lint commands for the chosen stack, directory layout, and hard constraints. Delete non-applicable template sections to conserve token budget.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/template-usage-guide.md 1.7 KB
- templates/AGENTS.md 955 B
- templates/CLAUDE.md 395 B
- templates/DESIGN.md 1.4 KB
- templates/docs/01-project-overview.md 930 B
- templates/docs/02-system-requirements.md 1.9 KB
- templates/docs/03-tech-stack-architecture.md 2.9 KB
- templates/docs/04-system-modeling.md 2.6 KB
- templates/docs/05-ux-ui-design.md 3.4 KB
- templates/README.md 959 B
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 · 85 lines · 218 tokens per session scan A 90876b582aac
project-docs-prep is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 2d ago), licensed MIT. It adds 218 tokens to every session and 1,180 once invoked, about $0.0011 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
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
release
Prepare, validate, and publish a Pake release. Not for version bumps without release intent.
pake
Package any website or local web build into a lightweight desktop app using Pake (Tauri/Rust). Use when the user wants to: wrap a URL as a native app, build a desktop app from a website or a local dist/ folder, use Pake CLI to package a page, set up proxy for a packaged app, customize app icons or bundle IDs, or…
data-fetching-architecture
LobeHub data-fetching pipeline guide. Use for service layer, Zustand store, SWR, lambdaClient, useClientDataSWR, useFetchXxx hooks, or migrating useEffect fetches.
deep-review
Multi-dimensional code review. Use when the user asks to review, evaluate, or audit a PR, diff, branch, or pasted change — including informal review asks like "look at this change for problems" — via light mode: one independent reviewer against the dimension quick checklists. Not for explain-only questions about what…
ux-audit
Audit a page / surface against the Designing Interfaces pattern language + the ux skill checklists, then land findings. Three layers — static (code), visual (screenshots), dynamic (automated user journey + perf). Use to run a repeatable, standards-based UX review of one screen.