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 Cratis/AI --skill cratis-governed-release-methodologygit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/cratis-governed-release-methodology)<a href="https://agentmods.dev/skills/cratis/ai/cratis-governed-release-methodology"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-governed-release-methodology/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/cratis/ai/cratis-governed-release-methodology"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-governed-release-methodology.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 | $0.00087 | $0.03339 |
| Opus 5.5 | $0.00035 | $0.01336 |
| Sonnet 5.5 | $0.00017 | $0.00668 |
| Haiku 4.5 | $0.00009 | $0.00334 |
Grade A, and why
cratis-governed-release-methodology 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 11d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Governed release methodology
Release engineering is the discipline of matching ceremony to consequence. Too little, and a consumer upgrades into a broken build with no way back. Too much, and every documentation fix drags a supply-chain ritual behind it until the ritual is performed without belief and stops meaning anything.
This skill is product-, language-, and registry-independent. It applies to a
Cratis repository publishing NuGet packages, one publishing npm packages, one
pushing container images, and one whose whole delivery is a merge to main. It
grants no release authority of its own: it tells you what a claim costs, not
that you may make it.
Start with the artifact, not the process
The single most expensive mistake is applying package-release ceremony to something that is not a package. Classify the artifact first.
| Artifact | What the consumer receives | Ceremony it earns |
|---|---|---|
| Compiled package (NuGet, npm, Maven, Hex), container image, installer | Opaque bytes built on infrastructure the consumer cannot inspect | Full supply-chain receipts |
| Generated or bundled tree assembled by a pipeline | Bytes that do not exist in any reviewed source tree | Full supply-chain receipts |
| Source files a host reads directly from a git ref (rules, skills, templates) | Exactly the reviewed content at a commit | Review and versioning only |
The dividing question is "can the consumer verify what they got against what was reviewed, without trusting our build?" If the host clones a git ref and reads the files, git's own content addressing already answers that: the tree hash is the checksum, the commit is the provenance, and the reviewed diff is the artifact. Generating a checksum file for that content, publishing an SBOM of markdown, and demanding a signed attestation before a folder may be read adds process without adding a guarantee. Say so plainly rather than performing it.
If the artifact is compiled or assembled, the opposite holds, and the supply-chain receipts below are not optional decoration.
What ships with it
2 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.
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.
- 11d ago Changed · -23 lines e4965bc46b30
- 1mo ago Changed · +6 lines 090fd49295a3
- 1mo ago First seen · 298 lines · 87 tokens per session scan A dd3f76ca2752
cratis-governed-release-methodology is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 3,339 once invoked, about $0.0003 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 2026-09-06.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…