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 runxhq/runx --skill releasegit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/release)<a href="https://agentmods.dev/skills/runxhq/runx/release"><img src="https://agentmods.dev/badge/skills/runxhq/runx/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/runxhq/runx/release"><img src="https://agentmods.dev/badge/skills/runxhq/runx/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.01141 |
| Opus 5.5 | $0.00009 | $0.00456 |
| Sonnet 5.5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
A release is a project-owned operation, not a universal shell recipe. This skill gives Runx one common governance sequence—prepare, describe, approve, publish, and independently verify—while leaving the actual build and provider commands in a versioned profile owned by the project.
Use it when a package or project already knows how to prepare, publish, and verify itself but needs one digest-bound approval and receipt chain around those commands. Do not use it to invent a release process for an unconfigured project or to replace the project's tests, packaging, or registry tooling.
A release profile is the project adapter. It declares exact argv commands that the project already owns; this skill validates their release semantics but does not recreate the project's release implementation.
Runx core owns bounded profile reads, path and symlink containment, command-plan digests, sanitized child environments, process-tree supervision, timeouts, credential redaction, and output evidence. Package JavaScript only validates the release profile and interprets the three release-specific provider states.
Use prepare to execute the profile's preparation command and produce an
evidence-bound release brief. Use the default release runner to approve the
exact publish plan, execute it without a shell, then run a separate verification
command. The publish command is refused if its normalized argv plan drifts after
approval. Publication is never inferred from an agent answer or a zero exit code.
Project profile
project_root is resolved inside the current Runx workspace and must be a
relative directory (normally . when Runx is invoked from the project root).
profile_path must name a JSON file inside that directory:
{
"schema": "runx/release.profile.v1",
"id": "my-project/npm",
"channel": "npm",
"commands": {
"prepare": { "argv": ["pnpm", "release:check"], "cwd": ".", "timeout_ms": 300000 },
"publish": { "argv": ["gh", "workflow", "run", "release.yml"], "cwd": "." },
"verify": { "argv": ["pnpm", "release:check:live"], "cwd": "." }
}
}
What ships with it
13 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.
- fixtures/release-exact-command-readback.yaml 1.7 KB
- fixtures/release-missing-profile.yaml 846 B
- fixtures/support/release-blocked-fixture.graph 436 B
- fixtures/support/release-fixture.graph 544 B
- fixtures/support/setup_release_fixture.mjs 2.6 KB runs code
- mark.svg 536 B
- packets/brief.v1.schema.json 5.1 KB
- packets/context.v1.schema.json 3.7 KB
- packets/phase_result.v1.schema.json 3.5 KB
- references/catalog.md 125 B
- references/mark-license.md 3.1 KB
- release.mjs 12 KB runs code
- run.yaml 12 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.
- 5d ago Changed 088103a00516
- 18d ago Changed · -2 lines 1fa7978a5f4f
- 1mo ago First seen · 115 lines · 23 tokens per session scan A 2d08998848cf
release is a skill published in the GitHub repository runxhq/runx (105 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 1,141 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
github
Skill "github" from Hmbown/Codewhale, covering github, when to use, setup, workflow and non-goals.
release
Skill "release" from Hmbown/Codewhale, covering release, invocation, non-goals and workflow.
release
Release Aigon — push to origin, cut a version+tag, or publish to npm. Wraps scripts/ship.js with CHANGELOG draft + dry-run preview. Triggers when the user types "/release", "/push", "/ship", or says "ship a release", "publish a beta", "cut a version", "push to origin", "release X to npm".
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.