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/iampawan/manifest/tutorialnpx skills add iampawan/Manifest --skill tutorialgit clone --depth 1 https://github.com/iampawan/ManifestWhat 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 | $0.00068 | $0.01990 |
| Opus 5 | $0.00034 | $0.00995 |
| Sonnet 5 | $0.00014 | $0.00398 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
tutorial 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 2d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manifest tutorial
You are giving a first-time user a quick orientation. Keep it conversational — they don't want a manual, they want to feel oriented enough to take a first action. Aim for under 3 minutes of their reading time.
Detect what kind of welcome to give
Read the user's input phrasing:
- "What is this?" / "/manifest" / "/contract" with no args → Give the 30-second overview, then offer three paths.
- "How do I use this?" / "tutorial" / "walk me through" → Give the guided walkthrough.
- "What are the options?" / "commands?" / "help" → Give the reference card.
Default to overview + paths if intent is unclear.
Always check setup first
Before doing anything else, invoke the setup-check skill briefly to see what's connected. Use the result to tailor the tutorial:
- If everything is connected: proceed normally.
- If something required is missing: tell the user upfront — "I see your Slack MCP isn't connected; that's required for the team workflow. Want me to walk through what to connect, then come back to the tutorial?"
- If recommended MCPs are missing: continue the tutorial but call out what features won't work yet — "JIRA-based intake won't work without the Atlassian MCP; we'll use free-text intake for the demo."
This way the user never gets surprised mid-flow by a missing MCP.
The 30-second overview
Start with this exact framing (rephrase naturally; don't read it verbatim):
Manifest takes a feature idea — a PRD, a JIRA ticket, or a one-line description — through a quality-gated pipeline from spec to production. Critics check the spec for completeness. An agent implements it. The system tracks whether the feature actually landed.
The contract — a structured markdown file — is the source of truth at every stage. Critics won't let a contract progress until required fields are filled. That's what prevents bugs at PRD time instead of production time.
Then ask:
Three ways to learn this:
- 🚀 Just try it — paste a JIRA ticket or describe a feature. I'll walk you through the rest.
- 📋 Show me a demo — I'll run through an example contract so you can see what the critics catch.
- 📖 Just the reference — show me the commands and options.
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.
- 2d ago First seen · 218 lines · 68 tokens per session scan A f77ec89416d9
tutorial is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 20d ago), licensed MIT. It adds 68 tokens to every session and 1,990 once invoked, about $0.0003 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.