Borrowing it
Nothing to install: this file belongs to flisk-sh/flisk. 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/flisk-sh/flisk/main/.claude/skills/flisk-release/SKILL.mdgit clone --depth 1 https://github.com/flisk-sh/fliskWrote 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/flisk-sh/flisk/flisk-release)<a href="https://agentmods.dev/skills/flisk-sh/flisk/flisk-release"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-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/flisk-sh/flisk/flisk-release"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-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 | $0.00112 | $0.02302 |
| Opus 5.5 | $0.00045 | $0.00921 |
| Sonnet 5.5 | $0.00022 | $0.00460 |
| Haiku 4.5 | $0.00011 | $0.00230 |
Grade C, and why
flisk-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 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.
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.
curl -s https://registry.npmjs.org/@flisk-sh%2fflisk | node -e 'let s="";process.stdin.on("data",d=>s+=d).on("end",()=>console.log(JSON.parse(s)["dist-tags"]))' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: Requires the gh CLI authenticated with write access to flisk-sh/flisk (and flisk-sh/releases for repairs), curl and Node 22+. Runs entirely through GitHub Actions; no local build is needed. How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing Flisk
The human version of this guide is docs/releasing.md. It holds the background, every troubleshooting row and the settings and secrets. This skill is the procedure. Read the doc's Troubleshooting table before you diagnose any red run.
Workflows (IDs are stable, names have emoji, so use the file name):
| File | What it does |
|---|---|
release-candidate.yml |
Packs the CLI, runs quickstart (Q1-Q4) and every release-blocking resource-type suite on that tarball, the longest suites first. Runs only on release/* branches and rc-* tags. ~5 min. With -f release=true it also dispatches release-binaries.yml on its own branch once every candidate job has passed (after gate), so a failed candidate starts no release. |
release-binaries.yml |
build → windows-binary → publish (gate, binaries to flisk-sh/releases, npm, signing, bump or tag) → publish-github-packages and publish-image. The MCP Registry listing is publish-mcp-registry.yml, started when the release run completes; repair it with gh workflow run publish-mcp-registry.yml -f version=<version>. ~6 min. |
sign-release.yml |
Signs an already published version after the fact. |
publish-existing-npm-to-github-packages.yml |
Backfills GitHub Packages for a version already on npm. |
1. Check the state before touching anything
gh run list -R flisk-sh/flisk -w release-binaries.yml -L 5
gh run list -R flisk-sh/flisk -w release-candidate.yml -L 5
gh release list -R flisk-sh/releases -L 3 # binaries: the real "latest"
gh release list -R flisk-sh/flisk -L 3 # checksums; a Draft here means a half-finished release
curl -s https://registry.npmjs.org/@flisk-sh%2fflisk | node -e 'let s="";process.stdin.on("data",d=>s+=d).on("end",()=>console.log(JSON.parse(s)["dist-tags"]))'
If recent release runs are red, read why (gh run view <id> --log-failed | grep -E "##\[error\]|FAIL") before dispatching again. A red publish gate (No passing Release candidate covers <sha>) is fixed by a candidate, never by re-dispatching. If a version is already on npm but its flisk-sh/flisk release is a draft or has no tag, go to step 6. Do not cut a new version.
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 First seen · 117 lines · 112 tokens per session scan C d96ec5b0be3d
flisk-release is a skill published in the GitHub repository flisk-sh/flisk (54 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 2,302 once invoked, about $0.0004 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 2026-11-15.
flisk-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flisk-releaseflisk-sh/flisk | Skill | 54 | yesterday | MIT | C | 112 | Claude Code |
| github-managerjpantsjoha/ai-native-developer-experience | Skill | 13 | 11d ago | Apache-2.0 | A | 38 | Claude Code |
| release-managerjpantsjoha/ai-native-developer-experience | Skill | 13 | 11d ago | Apache-2.0 | A | 64 | Claude Code |
| releasebuild-with-dhiraj/ai-workflow-framework-portability-kit | Skill | 5 | 1mo ago | MIT | A | 43 | Claude Code |
| changelog-automatorAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 27 | Claude Code, Codex |
| changelog-generatorAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 24 | Claude Code, Codex |
| semantic-versioningAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 24 | Claude Code, Codex |