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/godshiba/genesis/initnpx skills add godshiba/genesis --skill initgit clone --depth 1 https://github.com/godshiba/genesisWhat 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 | $0.00109 | $0.01671 |
| Opus 5 | $0.00055 | $0.00835 |
| Sonnet 5 | $0.00022 | $0.00334 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
init 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/genesis:init — The GENESIS Prep Protocol
Source of truth: the plugin's MASTER.md (doctrine) and templates/
(CLAUDE.template.md + registry skeletons). Both live at the plugin root —
two directories above this skill's base directory, i.e. ../../MASTER.md
and ../../templates/ from here. Read both before generating anything. Do
not improvise structure that the templates already define.
The doctrine in one line: what isn't registered doesn't exist. The output of this skill is a project where that is mechanically true from day zero.
Mode Detection
Inspect the working directory first:
- Greenfield (empty, or no source code): run all five steps below.
- Existing repo: skip interview questions the repo already answers. Detect
stack and commands from manifests (package.json, Package.swift, Cargo.toml,
pyproject.toml, go.mod, Makefile), derive the dependency graph from imports,
and mine git history plus existing docs for landmines and decisions already
paid for. Read existing design specs by shape, not by origin —
docs/specs/,adr/,rfc/, PRDs, design docs, or a tool's own spec folder (a generated*-design.mdcounts) — and lift each one's chosen approach and rejected alternatives intoDECISIONS.md(citing the spec), its open questions intoISSUES.md, even when there are too few docs to trigger/genesis:docs. Then run only the steps with gaps (usually Interrogate's out-of-scope question and Phase). If the repo carries more than a handful of doc files, offer the/genesis:docscuration protocol as part of the retrofit — it inventories every doc, absorbs registry-shaped knowledge (decisions, gotchas, TODO lists) into the new registries, and reorganizes the rest behind an approval gate. - Already has a CLAUDE.md: do not overwrite. Read it, map its content onto the template slots, propose a migration diff, and get approval first.
Calibrating to the user
If the user seems new to Claude Code (asks what a step is for, or says so), briefly explain each step's purpose as you go and include the "Why these gates exist" pointer in the generated CLAUDE.md. If the user is clearly experienced, be terse: ask, decide, generate. Never skip steps in either mode — calibration changes narration, not rigor.
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 · 135 lines · 109 tokens per session scan A d5cbc1c75b1c
init is a skill published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 1,671 once invoked, about $0.0005 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
aip-tracker
Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
devops
DevOps 能力索引。Git、测试、DevSecOps、数据库。当用户提到 DevOps、CI/CD、Git、测试时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:create-pr
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.