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/sapiom/sapiom-js/release-desktopnpx skills add sapiom/sapiom-js --skill release-desktopgit clone --depth 1 https://github.com/sapiom/sapiom-jsWhat 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 | $0.00103 | $0.01732 |
| Opus 5 | $0.00051 | $0.00866 |
| Sonnet 5 | $0.00021 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
release-desktop 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing the Sapiom Studio desktop app
The desktop app ships as signed installers (dmg/zip on macOS, AppImage/deb on
Linux, nsis on Windows), NOT to npm. A release is cut by pushing a git tag on
main; version bumping is handled by changesets first.
The invariant that governs everything
The tag must equal packages/harness-desktop/package.json's version
exactly (e.g. tag v0.2.4 ⇔ version 0.2.4). The
desktop-release.yml prepare job fails fast on a mismatch. package.json — not
the tag — is the source of truth for the artifact names and the app's self-reported
version and update channel.
Tag conventions (drive the update channel)
| Tag | Release | Channel |
|---|---|---|
v1.2.3 |
final | latest (everyone) |
v1.2.3-beta.1 |
pre-release | beta (opted-in only) |
workflow_dispatch (manual run of desktop-release.yml) builds artifacts only — no
tag, no publish. Useful to smoke a build without releasing.
The full flow
-
Every fix/feature PR carries a changeset.
.changeset/<name>.mdwith the bumped package(s) and a summary. Format:--- "@sapiom/harness-desktop": patch "@sapiom/harness": patch --- One-paragraph, user-facing description of the change.- A change only in
@sapiom/harnessneeds only that entry —harness-desktopgets a patch bump automatically (changeset configupdateInternalDependencies: "patch", since it depends on@sapiom/harnessviaworkspace:^). But if you want the desktop CHANGELOG to describe a desktop-side fix, add an explicit@sapiom/harness-desktopentry too. - If a PR merged without a changeset, its fix ships silently (no changelog
entry). Add the missing changeset before releasing — a later PR's changeset
file is fine; changesets are just release-note artifacts on
main. - Check coverage:
ls .changeset/*.md(ignore README.md) and read each header.
- A change only in
-
Merge the PRs to
main. Changesets accumulate onmain.
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.
- 2d ago First seen · 117 lines · 103 tokens per session scan A 64d821369e81
release-desktop is a skill published in the GitHub repository sapiom/sapiom-js (19 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 1,732 once invoked, about $0.0005 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 2026-08-30.
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…