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 joacod/skills --skill safe-pnpm-updatergit clone --depth 1 https://github.com/joacod/skillsWrote 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/joacod/skills/safe-pnpm-updater)<a href="https://agentmods.dev/skills/joacod/skills/safe-pnpm-updater"><img src="https://agentmods.dev/badge/skills/joacod/skills/safe-pnpm-updater/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/joacod/skills/safe-pnpm-updater"><img src="https://agentmods.dev/badge/skills/joacod/skills/safe-pnpm-updater.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00086 | $0.02449 |
| Opus 5.5 | $0.00034 | $0.00980 |
| Sonnet 5.5 | $0.00017 | $0.00490 |
| Haiku 4.5 | $0.00009 | $0.00245 |
Grade A, and why
safe-pnpm-updater 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe pnpm updater
Select the newest stable versions within the requested scope that satisfy release-age, security, and compatibility checks. Discover the project's stack and verification commands instead of assuming a framework or application. Defer candidates that cannot be validated and report the concrete blocker. Passing tests and a clean audit are evidence, not proof of complete safety.
Scope and authorization
- Read repository instructions and inspect the working tree before edits. Preserve unrelated changes; ask before taking ownership of pre-existing dependency-file changes. Capture the starting contents of files this run may change so recovery can preserve those changes.
- Determine the package manager from
packageManager, lockfiles, workspace configuration, and CI. Stop on conflicting evidence. For npm, Yarn, or Bun, report unsupported execution; do not migrate the project to pnpm. - An update request covers its requested local dependency changes, subject to repository authorization rules. Audit/review requests cover investigation only. Installing existing dependencies does not authorize upgrading them.
- Explain candidate groups before editing. Ask about major versions when scope is unclear. For an unrestricted "update all" request, consider every direct dependency, including majors, but obtain any required confirmation for a non-trivial migration. Do not turn an update into a redesign.
- Do not branch, commit, push, create a PR, deploy, publish, send messages, or modify remote environments without authorization for those actions. Inspect validation scripts for uploads, paid calls, production access, and destructive behavior before running them.
1. Verify the security boundary
Resolve bundled scripts relative to this skill's installed directory, not a hardcoded repository path. From the project or workspace root:
bash "<skill-directory>/scripts/check-prerequisites.sh" "$PWD"
The preflight requires the exact interactive zsh alias sfw --verbose pnpm,
an executable sfw, Socket Firewall runtime confirmation, and a positive
effective minimumReleaseAge in minutes. It performs version and configuration
checks, without registry lookups or installation.
What ships with it
3 files 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.
- 2d ago First seen · 230 lines · 86 tokens per session scan A 6e57df4ff5e5
safe-pnpm-updater is a skill published in the GitHub repository joacod/skills (3 stars, last pushed 3d ago), licensed MIT. It adds 86 tokens to every session and 2,449 once invoked, about $0.0003 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 2026-10-01.
Other skills, from other repositories
developing-genkit-js
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.
antfu
Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.
adk
Use this skill when you've got questions about the Botpress Agent Development Kit (ADK) - like when you're building a feature that involves tables, actions, tools, workflows, conversations, files, knowledge bases, triggers, or Zai.
setup-ts-deep-modules
A setup for TypeScript packages that hides their implementation behind files at the package root. Dependency-cruiser checks that outside code uses these entry points, prevents dependency cycles, and keeps internal folders private.
aws-lambda-typescript-integration
Provides AWS Lambda integration patterns for TypeScript with cold start optimization. Use when creating or deploying TypeScript Lambda functions, choosing between NestJS framework and raw TypeScript approaches, optimizing cold starts, configuring API Gateway or ALB integration, or implementing serverless TypeScript…
aws-cdk
Provides AWS CDK TypeScript patterns for defining, validating, and deploying AWS infrastructure as code. Use when creating CDK apps, stacks, and reusable constructs, modeling serverless or VPC-based architectures, applying IAM and encryption defaults, or testing and reviewing cdk synth, cdk diff, and cdk deploy…