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 skills add kensaurus/cursor-kenji --skill deploy-npmgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/deploy-npm)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/deploy-npm"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/deploy-npm/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/kensaurus/cursor-kenji/deploy-npm"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/deploy-npm.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 338 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 MCP Rug Pull · line 124 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00050 | $0.03710 |
| Opus 5.5 | $0.00020 | $0.01484 |
| Sonnet 5.5 | $0.00010 | $0.00742 |
| Haiku 4.5 | $0.00005 | $0.00371 |
Grade A, and why
deploy-npm 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 1mo 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 — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deploy-npm — Full release workflow
Degree of freedom: MIXED. Semver/changeset judgment [HIGH freedom];
git/gh/npm publish steps [LOW freedom — run exactly]. Never pnpm publish
locally when the repo uses Trusted Publisher.
How to reason
- Observe — branch, dirty tree, open PRs, pending changesets, release.yml trigger
- Interpret — is this a changeset-ready release or a no-op?
- Classify — proceed / stop-and-ask (dirty tree, conflicting PRs, no changeset)
- Severity — publishing the wrong bump or skipping verify is a user-facing break
Worked example
Observe: feature PR green; one minor changeset; Version PR opened by the bot; required checks never fired. Interpret: GitHub anti-loop suppressed CI on the bot branch. Classify: empty-commit to trigger CI (Phase 4), then merge Version PR. Verify:
npm viewshows the new version; do not publish from the laptop.
Self-critique before reporting
- Phase order — no publish before version PR + green CI
- Verify —
npm view(and GH Release) ran after publish, not assumed - No local publish — Trusted Publisher path only
- Right owner — running app deploy →
workflow-ship-and-observe
This skill is opinionated for repos that use:
pnpm+turbomonorepo@changesets/cli+@changesets/actionfor versioning and changelog generation- A GitHub Actions workflow named
Release(.github/workflows/release.yml) that runschangeset version+changeset publishon push tomaster - npm Trusted Publisher (OIDC) with provenance — no long-lived
NPM_TOKEN step-security/harden-runnerblocking some runner writes (notably git tag refs)
Adapt the package / branch / workflow names if the target repo differs, but keep the phase order — every phase blocks on the previous one.
Quick Start
Copy this checklist into the conversation and tick boxes as you go:
Release progress:
- [ ] Phase 0: Discover repo state (branch, open PRs, pending changesets)
- [ ] Phase 1: Author / verify the changeset
- [ ] Phase 2: Green the feature PR
- [ ] Phase 3: Merge feature PR to master
- [ ] Phase 4: Wait for & green the changesets Version PR
- [ ] Phase 5: Merge Version PR → trigger publish
- [ ] Phase 6: Handle github-actions[bot] anti-loop if push trigger didn't fire
- [ ] Phase 7: Verify on npm (npm view) and on GitHub Releases
- [ ] Phase 8: Create per-package GitHub Release notes if harden-runner blocked tags
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · -6 lines 404ceed66598
- 1mo ago First seen · 401 lines · 50 tokens per session scan A e7d96ce57263
deploy-npm is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 27d ago), licensed MIT. It adds 50 tokens to every session and 3,710 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
bumpup-versions
Consistently bump and synchronize versions across all packages in the monorepo using pnpm. Use this to ensure the root and all workspace packages share the same version number.
manage-changelog
Manage changelogs using Changie. Provides tools to initialize, add change fragments, batch releases, and merge version notes. Requires 'changie' to be installed.
changelog-writer
Generates changelogs and release notes from git commits, PR titles, and issue references. Organizes changes by impact type (breaking, features, fixes, improvements), formats according to Keep a Changelog standard, and provides version tagging and semantic versioning suggestions. Use when users request "create…
deployment-checklist-generator
Creates comprehensive deployment checklists with pre-deployment checks, smoke tests, verification steps, and sign-off workflows. Use for "deployment checklist", "release verification", "deployment runbook", or "production readiness".
release-automation-builder
Automates releases and package publishing with changesets or semantic-release. Handles versioning, changelog generation, git tags, and release notes. Use for "release automation", "semantic versioning", "package publishing", or "changelog generation".
changelog
Changelog Generation Command 📝.