Borrowing it
Nothing to install: this file belongs to aterrylu/autonomOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aterrylu/autonomOS/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/aterrylu/autonomOSWrote 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/aterrylu/autonomos/release)<a href="https://agentmods.dev/skills/aterrylu/autonomos/release"><img src="https://agentmods.dev/badge/skills/aterrylu/autonomos/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/aterrylu/autonomos/release"><img src="https://agentmods.dev/badge/skills/aterrylu/autonomos/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 | $0.00120 | $0.02992 |
| Opus 5.5 | $0.00048 | $0.01197 |
| Sonnet 5.5 | $0.00024 | $0.00598 |
| Haiku 4.5 | $0.00012 | $0.00299 |
Grade C, and why
release scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
📦 **Install / upgrade:** `curl -fsSL https://raw.githubusercontent.com/aterrylu/autonomOS/main/scripts/install.sh | sh && autonomos start` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
📦 **Install / upgrade:** `curl -fsSL https://raw.githubusercontent.com/aterrylu/autonomOS/main/scripts/install.sh | sh && autonomos start` How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release — friendly release-notes rewrite
autonomOS ships release notes in two layers (see ADR-044):
- Floor of correctness — the mechanical, one-line-per-PR body that
scripts/sync-changelog.tsconsolidates intoCHANGELOG.mdandscripts/release-notes.tsextracts. CI publishes this automatically. It is always correct and never themed. - Ceiling of friendliness — the themed/emoji body Terry approved for
v0.3.0. That is what this skill produces.
This skill is the ceiling. The model doing the rewrite is the Claude Code session running this skill — there is no API key, no Anthropic SDK call, and no CI step. You read the mechanical body, transform it, and apply it to the live release. Because the mechanical floor already shipped from CI, this is a safe, reversible enhancement of an already-correct release body.
The spec is
canonical-example.md. Read it in full before writing anything. It is the exactv0.3.0mechanical→friendly pair. Match its structure, density, and tone. Do not try to be cleverer than the example — consistency with it IS the goal.
Preconditions: gh must be authenticated (gh auth status) and bun
available. If gh isn't logged in, step 1's commands fail with an auth error —
that is an auth problem, NOT a missing release; don't tell the user to publish one.
Procedure
1. Determine the version and tag
- If the user gave a version/tag, use it. Otherwise derive the version from
packages/server/package.json(.version) — that is the just-released version. - The bare version is e.g.
0.4.0. The tag isv0.4.0(version with a leadingv). Keep them distinct —release-notes.tswants the bare version;ghwants the tag. - Confirm the release exists and is published:
gh release view "v<version>" --json tagName,isDraft,bodyIf it doesn't exist, STOP and tell the user — this skill enhances a published release; it does not create one.
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.
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.
- 1mo ago Changed · +16 lines 62d536771005
- 1mo ago First seen · 221 lines · 120 tokens per session scan C 0e1fb6688b20
release is a skill published in the GitHub repository aterrylu/autonomOS (10 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 2,992 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
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.
deploy-steward
Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.