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 jesseposner/metacraft --skill genesisgit clone --depth 1 https://github.com/jesseposner/metacraftWrote 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/jesseposner/metacraft/genesis)<a href="https://agentmods.dev/skills/jesseposner/metacraft/genesis"><img src="https://agentmods.dev/badge/skills/jesseposner/metacraft/genesis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jesseposner/metacraft/genesis"><img src="https://agentmods.dev/badge/skills/jesseposner/metacraft/genesis.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.01142 |
| Opus 5.5 | $0.00009 | $0.00457 |
| Sonnet 5.5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
genesis 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 2mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genesis
Bootstrap a new multi-agent project from scratch. Resist the urge to start working. Close the circle first.
What this is
The genesis protocol is for the moment when you have a clear vision, capable tools, and the temptation to immediately start building. The protocol says: not yet. First, define how you'll work. Then resolve every open question. Then codify the process and persist the state. Then, and only then, begin.
This isn't bureaucracy. It's the recognition that the first ten minutes of a multi-agent project set the trajectory for everything that follows. Ambiguity that isn't resolved now becomes confusion that compounds later, across every agent, every lane, every handoff.
The same protocol works for rebooting a project that has lost coherence. When lanes have drifted, when nobody's sure what the agreements are, when the state files are stale: that's a genesis moment. Stop. Re-close the circle. Then resume.
When to use it
- Starting a new project that will involve multiple agents or work streams
- Rebooting a project that has lost coherence
- Any time you're about to spin up workers and realize you haven't agreed on how they'll coordinate
The pattern
Genesis has two phases: setup (define the meta-process) and initialization (make it real). Don't skip to initialization. The definitions have to be sharp before they can be codified.
Phase 1: Setup
Define the meta-process itself. This is constitutional: you're deciding how work will happen before any work begins.
Define the roles. Who does what. Not just "agent A writes code." Specifically:
- What types of agents are available (research, planning, coding, meta)
- What harness each one runs in, and why (different tools have different strengths)
- How the human operator and the meta-agent divide responsibility (see Meta-Agent for the boundary)
Define the feedback loops. How agents report back. This is where most multi-agent projects silently fail:
- Work agents should persist significant outputs to files at known locations, not just in chat
- The human relays chat outputs to the meta-agent as needed
- The meta-agent can read persisted artifacts directly or spin up a sub-agent to review them
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.
- 2mo ago First seen · 80 lines · 23 tokens per session scan A 568962415ffd
genesis is a skill published in the GitHub repository jesseposner/metacraft (11 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,142 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.