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/brew-publishnpx skills add SocketDev/sauce --skill brew-publishgit 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 | $0.00061 | $0.00809 |
| Opus 5 | $0.00030 | $0.00404 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
brew-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 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Homebrew tap (binary-download formula)
Model: no bottles, no source build - the formula downloads the release's
prebuilt per-platform tarballs by EXACT
releases/download/v<version>/<asset> URL (never latest) and pins the
sha256 the release's own checksums.txt vouched for. brew-publish NEVER
hashes an asset itself; the manifest is the authority.
Tap layout (one-time, manual)
The tap repo (SocketDev/homebrew-socket) carries an unsharded Formula/
dir plus a README documenting tap trust:
export HOMEBREW_REQUIRE_TAP_TRUST=1
brew trust SocketDev/socket
The exact layout is modeled by release-kit/examples/brew-cli/tap-fixture/
in sauce. Creating the tap repo is a human act (repo creation rights) -
note it plainly; there is no script.
Bump cycle
Prerequisite: the release is CUT - tag on origin, release published (not
draft), all four platform assets uploaded, checksums.txt attached (the
github-release flow produces all of this).
node scripts/socket-release/brew-publish.mts --tag vX.Y.Z # dry-run plan
node scripts/socket-release/brew-publish.mts --tag vX.Y.Z --apply # commit the bump
The tool refuses, in order, with exit 1 and zero writes: a tag not on
origin (it never creates tags), a draft/missing release, a missing
templated asset, a missing/incomplete checksums.txt. An identical formula
is a no-op ("already reads ", exit 0). --apply commits the
formula DIRECT to the tap default branch with a GitHub-signed API commit
(never a PR - the version-bump-PR shape is guard-blocked), then re-reads
the tap: the committed bytes must parse back to the desired formula, or it
exits 1 saved-state-unproven.
From CI, brew-publish.yml runs on release: published (or manual
dispatch with tag + publish: true) and mints a per-run App token via
the ./.github/actions/socket-release-app-token composite from the
org-wide App credentials - org secrets are enterprise-wide; never treat
them as missing setup or a human task.
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 · 78 lines · 61 tokens per session scan A 812f5961eff0
brew-publish is a skill published in the GitHub repository SocketDev/sauce (2 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 809 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…