cratis-governed-release-methodology

cratis-governed-release-methodology is a skill for Claude Code, Codex from Cratis/AI. It costs 87 tokens per session (3,520 once invoked), scanned A, original, MIT.

A release-planning guide for deciding how much evidence and checking a software release needs. It covers release impact, checksums, provenance, software bills of materials, canary releases, and recovery decisions.

In plain words
What is it for?
Use it to plan releases, select an assurance level, gather supply-chain evidence, label semantic-version impact, and prepare a canary-before-promotion path.
Why use it?
It helps teams avoid both unsafe releases and unnecessary process. The approach first identifies what consumers receive, such as a package, container image, or application change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan releases, select an assurance level, gather supply-chain evidence, label semantic-version impact, and prepare a canary-before-promotion path.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cratis/ai/cratis-governed-release-methodology
View source ↗ Cratis/AI
Install

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.

Any agent
npx skills add Cratis/AI --skill cratis-governed-release-methodology
Clone the repo
git clone --depth 1 https://github.com/Cratis/AI

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for cratis-governed-release-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/cratis/ai/cratis-governed-release-methodology/github.svg)](https://agentmods.dev/skills/cratis/ai/cratis-governed-release-methodology)
Your own site
<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.

agentmods 80×15 button for cratis-governed-release-methodology

Your own site · 80×15
<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>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,520 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.03520
Opus 5 $0.00044 $0.01760
Sonnet 5 $0.00017 $0.00704
Haiku 4.5 $0.00009 $0.00352

Measured 2d ago against content hash dd3f76ca2752, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 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.

skills/cratis-governed-release-methodology/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 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.

Read the full file on GitHub · 298 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2d ago First seen · 298 lines · 87 tokens per session scan A dd3f76ca2752

Subscribe to this mod's changes

cratis-governed-release-methodology is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 3,520 once invoked, about $0.0004 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 2026-09-06.