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 hxy91819/mason-skills --skill secure-releasegit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote 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/hxy91819/mason-skills/secure-release)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/secure-release"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/secure-release/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/hxy91819/mason-skills/secure-release"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/secure-release.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 | $0.00082 | $0.00793 |
| Opus 5 | $0.00041 | $0.00396 |
| Sonnet 5 | $0.00016 | $0.00159 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
secure-release 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure Release
这是流程类 Skill，默认仅在用户显式调用 $secure-release 时运行。
Keep the agent-facing integration workflow separate from the runtime release components. A target repository's CI must work after this skill is removed.
Workflow
- Inspect repository instructions, Git state, manifests, release workflows, changelog policy, registry configuration, and existing published releases.
- Read protocol.md and classify each invariant as present, missing, conflicting, or not applicable.
- Read adapters.md. Select only an adapter whose status is implemented. Treat all other ecosystems as design targets, never as supported release paths.
- Prefer the versioned vendored kit in
assets/secure-release-kit/v1/for the shared deterministic checks. Copy it into the target repository, normally under.github/secure-release/v1/, and retain its tests. - Create or migrate a thin workflow in the target repository. Keep its exact path, GitHub Environment, permissions, trigger, project checks, and adapter commands visible there. Pin external actions to reviewed commit SHAs.
- Configure the registry Trusted Publisher out of band using the target repository, exact workflow filename, and Environment shown in the thin workflow. Never put that identity in a reusable workflow hidden elsewhere.
- Exercise
--help, unit tests, an offline fixture release, and fail-closed negative cases before enabling publication. Verify the packed contents. - Run repository checks, privacy and Git-metadata review, then independently review the final workflow and kit diff.
Migration Rules
- Preserve an existing release trigger until the replacement has an explicit cutover decision. Do not leave two workflows able to publish one version.
- Build once in preflight, upload one named artifact bundle, and publish only downloaded bytes that pass the manifest SHA-256 check. Never rebuild in the privileged publish job.
- Resolve the tag, version, commit, manifest, registry identity, and GitHub Release identity independently. Any mismatch or ambiguous network error is a hard failure.
- Treat registry publication as irreversible. A rerun may verify an already published exact version, but must not silently overwrite or repoint it.
- Keep project-specific build, test, package-content, and smoke assertions in the thin workflow or adapter configuration, not in the common protocol.
- Do not require a Codex installation, this skill directory, or network access to this repository during CI execution.
What ships with it
7 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.
- agents/openai.yaml 265 B
- assets/secure-release-kit/v1/npm-release.yml 7.2 KB
- assets/secure-release-kit/v1/secure_release.py 19 KB runs code
- assets/secure-release-kit/v1/test_secure_release.py 12 KB runs code
- references/adapters.md 2.3 KB
- references/component-boundaries.md 1.5 KB
- references/protocol.md 2.9 KB
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.
- 7d ago Changed · +3 lines 88b5313fd22e
- 11d ago First seen · 66 lines · 82 tokens per session scan A c1d43150e310
secure-release is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 793 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…