Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/loopdive/js2npx agentmods add skills/loopdive/js2/publish-releaseWrote 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/loopdive/js2/publish-release)<a href="https://agentmods.dev/skills/loopdive/js2/publish-release"><img src="https://agentmods.dev/badge/skills/loopdive/js2/publish-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/loopdive/js2/publish-release"><img src="https://agentmods.dev/badge/skills/loopdive/js2/publish-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 137 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 22 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00183 | $0.02578 |
| Opus 5.5 | $0.00073 | $0.01031 |
| Sonnet 5.5 | $0.00037 | $0.00516 |
| Haiku 4.5 | $0.00018 | $0.00258 |
Grade A, and why
publish-release scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
not the egress proxy — `curl -sS "$HTTPS_PROXY/__agentproxy/status"` showing How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/publish-release — cut a release and push the version tag
Two npm packages ship in lockstep, plus JSR:
| package | manifest |
|---|---|
@loopdive/js2 |
root package.json |
js2wasm (proxy that re-exports the scoped package) |
packages/js2wasm/package.json |
.github/workflows/publish-npm.yml fires on any v* tag push and publishes
all three. The authoritative reference is
docs/releasing.md; this skill is the operator
protocol on top of it.
The one thing that makes this dangerous
Pushing the tag IS the publish. There is no confirmation step and no
practical undo — npm unpublish is heavily restricted, and JSR versions are
immutable. Everything below exists so the tag goes up exactly once, pointing at
reviewed code that is already on main.
So the ordering is not stylistic:
Push the branch. Get it merged. Only then push the tag.
A tag pushed before merge publishes un-reviewed code to the public registry.
Never hand-write a version tag (#389)
git tag vX.Y.Z on its own is the bug this flow was built to kill. The publish
workflow ships whatever version field package.json carries at the tagged
commit — not the tag name. Releases used to be bare tags that never touched
the manifest, so the published version sat pinned at 0.52.0 across thousands
of commits while the tags kept climbing. An external tester found it.
Two consequences worth holding onto:
- Version tags come exclusively from
scripts/release.mjs. If you catch yourself typinggit tag v…, stop — you are re-introducing #389. - Sprint-end tags
sprint/N, nevervX.Y.Z. The two are unrelated.
Step 1 — bump, commit, tag (one command, clean tree)
node scripts/release.mjs 0.70.0 # explicit version
node scripts/release.mjs patch # or a semver keyword: patch | minor | major
The script resolves one concrete version and applies the same string to four
places: the root manifest, the proxy manifest, the proxy's
dependencies["@loopdive/js2"], and jsr.json (which carries its own version
field and is what JSR publishes). Then it makes one commit
release: vX.Y.Z and one annotated tag vX.Y.Z on your branch. It also drafts
docs/release-notes/vX.Y.Z.md from the commit subjects since the last release
tag, amends it into the commit, and re-points the tag. Finally it runs
pnpm run refresh:benchmarks and, if tracked files under benchmarks/results/
changed, commits them as chore(benchmarks): refresh for vX.Y.Z on top of the
tagged commit, so the numbers are reviewed in the release PR (--skip-benchmarks
opts out; a failed refresh only warns). This used to be a side effect of
pushing the tag, inside .husky/pre-push (#6799).
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.
- 14d ago Changed · +6 lines 0049ae90a220
- 1mo ago First seen · 212 lines · 183 tokens per session scan A a4b983ad6c3c
publish-release is a skill published in the GitHub repository loopdive/js2 (67 stars, last pushed today), licensed Apache-2.0. It adds 183 tokens to every session and 2,578 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
draft-release-notes
Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
triage-contributor-pr
Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.