trusted-publish

trusted-publish is a skill for Claude Code, Codex from soulmachine/skills. It costs 0 tokens per session (941 once invoked), scanned A, original, MIT.

A procedure for turning a project’s feature list into detailed product requirement documents, with each document describing one feature.

In plain words
What is it for?
Use it after FEATURES.md has been created when you need a separate PRD—a document describing what a feature should do—for an individual feature.
Why use it?
It provides the specification step between knowing which user-facing features exist and building them.

Skill for Claude CodeCodex

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

Good fit Use it after FEATURES.md has been created when you need a separate PRD—a document describing what a feature should do—for an individual feature.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soulmachine/skills/trusted-publish
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 soulmachine/skills --skill trusted-publish
Clone the repo
git clone --depth 1 https://github.com/soulmachine/skills

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 trusted-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/soulmachine/skills/trusted-publish/github.svg)](https://agentmods.dev/skills/soulmachine/skills/trusted-publish)
Your own site
<a href="https://agentmods.dev/skills/soulmachine/skills/trusted-publish"><img src="https://agentmods.dev/badge/skills/soulmachine/skills/trusted-publish/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 trusted-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/soulmachine/skills/trusted-publish"><img src="https://agentmods.dev/badge/skills/soulmachine/skills/trusted-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 941 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 $0.00000 $0.00941
Opus 5 $0.00000 $0.00470
Sonnet 5 $0.00000 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 9d ago against content hash 05632cfacd75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

trusted-publish 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 9d 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.

trusted-publish/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

trusted-publish

Every registry here is push-model: the registry never pulls or builds — a GitHub Actions workflow builds and uploads. Trusted publishing makes that upload tokenless: the workflow proves its identity over OIDC and the registry mints a short-lived, auto-expiring upload token. Setup is therefore three artifacts: a workflow in the repo, a trust entry on the registry, and a release to trigger the run.

The trust entry binds four identity fields — owner, repository, workflow filename, environment. The workflow file is the credential: these values must match the registry config character-for-character. This skill fixes them — workflow .github/workflows/publish-<registry>.yml, environment named after the registry — so every run produces the same names and the user types the same values.

Steps

  1. Resolve the repo. The argument, when given, is the repo path; otherwise use the current directory. Record owner/repo from git remote get-url origin. Done when the path is a git repo with a github.com origin. A GitLab origin narrows provider support — check the reference file's provider line before continuing; any other host means trusted publishing is unavailable: report that and stop.

  2. Detect every ecosystem. Walk the repo for package manifests and map each to its registry:

    Manifest Registry Reference
    pyproject.toml / setup.py PyPI references/pypi.md
    package.json without "private": true npm references/npm.md
    Cargo.toml with a [package] section and publish not disabled crates.io references/crates-io.md
    *.gemspec, *.nuspec, anything else varies references/other-registries.md

    Done when every manifest in the repo is either mapped to a registry or reported to the user as out of scope. Several matches (a monorepo) → run steps 3–6 once per registry.

Read the full file on GitHub · 34 lines

Files

What ships with it

4 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.

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. 9d ago First seen · 34 lines · 0 tokens per session scan A 05632cfacd75

Subscribe to this mod's changes

trusted-publish is a skill published in the GitHub repository soulmachine/skills (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 941 tokens. 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.