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 agentmods add skills/socketdev/sauce/github-releasenpx skills add SocketDev/sauce --skill github-releasegit clone --depth 1 https://github.com/SocketDev/sauceWhat 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 | $0.00070 | $0.00678 |
| Opus 5 | $0.00035 | $0.00339 |
| Sonnet 5 | $0.00014 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
github-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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub release (immutable, registry-gated)
ORDER RULE (non-negotiable): the immutable GitHub release is the FINAL
marker of a release. It can only follow a version that already resolves on
its registry - never precede one. requireRegistryLive enforces this in
every path; the github-release.yml workflow's gate job refuses a pushed
tag whose version is not live (registry-liveness-gate.mjs, zero-dep, runs
before any install).
Normal path (automatic)
The npm/cargo promote tail cuts the tag + release itself: after
node scripts/socket-release/npm-publish.mts --approve promotes and the
version resolves live, the engine tags v<version>, pushes the tag, and
cuts the release. Nothing to run by hand when that succeeds.
Cutting a release with assets
github-release.mts --release performs the fleet-canonical three-step immutable
cut - gh release create --draft --verify-tag → upload assets → gh release edit --draft=false — and writes a checksums.txt manifest (sha1 + sha256 +
sha512) alongside the tarball, so the GitHub-release digest stays directly
comparable to the npm published shasum:
node scripts/socket-release/github-release.mts --tag vX.Y.Z --release
Never hand-run gh release create without --draft: the release goes
immutable the instant it publishes, so assets and checksums must be attached
while drafted.
Healing a release gap
A RELEASE GAP is a version public on its registry with the v<version> tag
or GitHub release missing. Re-running --approve does NOT heal it (the
approve leg drops already-published versions before the tag step). The
healer is:
node scripts/socket-release/github-release.mts --tag vX.Y.Z # dry-run: confirms liveness
node scripts/socket-release/github-release.mts --tag vX.Y.Z --release # cuts tag + release
It refuses (exit 1) when the version is not live - an unreachable registry
is never read as unpublished. From CI, the operator dispatches the
github release workflow with tag + release: true from the Actions UI
(gh workflow run is guard-blocked for agents - the human clicks; there is
no agent lane for the dispatch itself).
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.
- yesterday First seen · 67 lines · 70 tokens per session scan A 3330ccb1a23d
github-release is a skill published in the GitHub repository SocketDev/sauce (2 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 678 once invoked, about $0.0003 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…