MCPInstall

pnpm-upgrade

by openai OfficialAI & Agents

Keep pnpm current: preflight the published package and pnpm/action-setup self-installer, update pnpm locally, align packageManager in package.json, and refresh CI pins. Use this when refreshing the pnpm toolchain manually or in automation.

Installs
143
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/openai/openai-agents-js --skill pnpm-upgrade
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads pnpm-upgrade automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

pnpm Upgrade

Use these steps to update pnpm and CI pins without blunt search/replace.

Steps (run from repo root)

  1. Resolve the target pnpm release

    • Query the npm registry before changing the local toolchain: PNPM_VERSION=$(curl -fsSL https://registry.npmjs.org/pnpm/latest | jq -r .version).
    • Abort if the version is missing.
    • Resolve the exact package integrity: curl -fsSL "https://registry.npmjs.org/pnpm/${PNPM_VERSION}" | jq -r .dist.integrity.
    • Store the result as PNPM_INTEGRITY.
    • Abort if the integrity is missing or does not start with sha512-.
    • Convert the base64 digest after sha512- to lowercase hex, for example:
      printf '%s' "${PNPM_INTEGRITY#sha512-}" | base64 -d | xxd -p -c 256
      
    • Store the result as PNPM_SHA512_HEX.
  2. Find the target pnpm/action-setup release

    • Query GitHub API: curl -fsSL https://api.github.com/repos/pnpm/action-setup/releases/latest | jq -r .tag_name.
    • Use GITHUB_TOKEN/GH_TOKEN if available for higher rate limits.
    • Store as ACTION_TAG (e.g., v4.2.0). Abort if missing.
  3. Resolve the action tag to an immutable commit SHA

    • Run git ls-remote https://github.com/pnpm/action-setup "refs/tags/${ACTION_TAG}^{}" and capture the SHA as ACTION_SHA.
    • If the dereferenced tag is missing, fall back to git ls-remote https://github.com/pnpm/action-setup "refs/tags/${ACTION_TAG}".
    • Abort if ACTION_SHA is empty.
  4. Preflight the release and CI installation path

    • Run node .agents/skills/pnpm-upgrade/scripts/preflight.mjs --version "${PNPM_VERSION}" --action-ref "${ACTION_SHA}".
    • The script first rejects published pnpm manifests with non-empty dependencies or devDependencies. pnpm bundles its runtime dependencies, so these fields indicate a broken publication such as pnpm@11.12.0.
    • It then reproduces both pnpm/action-setup installation paths in separate temporary directories: install the regular pnpm bootstrap from pnpm-lock.json and the standalone @pnpm/exe bootstrap from exe-lock.json, set isolated PNPM_HOME directories, and self-update each bootstrap to PNPM_VERSION.
    • Abort the upgrade on any failure. Do not bypass this check with a direct local install; the preflight exists to exercise the CI-only bootstrap path.
  5. Update pnpm locally

    • Run pnpm self-update "${PNPM_VERSION}".
    • If pnpm is missing or self-update fails only because the current installation cannot update itself, run corepack prepare "pnpm@${PNPM_VERSION}" --activate. Do not use this fallback to bypass a failed preflight.
    • Confirm pnpm -v exactly matches PNPM_VERSION.
  6. Align package.json

    • Open package.json and set packageManager to pnpm@${PNPM_VERSION}+sha512.${PNPM_SHA512_HEX} (preserve trailing newline and formatting).
  7. Update workflows carefully (no broad regex)

    • Files: everything under .github/workflows/ that uses pnpm/action-setup.
    • For each file, edit by hand:
      • Set uses: pnpm/action-setup@${ACTION_SHA}.
      • If a with: version: field exists, set it to ${PNPM_VERSION} (keep quoting style/indent).
    • Do not touch unrelated steps. Avoid multiline sed/perl one-liners.
  8. Verify

    • Run pnpm -v and confirm it matches the version portion of packageManager.
    • Confirm packageManager keeps the exact +sha512.${PNPM_SHA512_HEX} suffix.
    • git diff to ensure only intended workflow/package.json changes.
  9. Follow-up

    • If runtime code/build/test config was changed (not typical here), run $code-change-verification; otherwise, a light check is enough.
    • Commit with chore: upgrade pnpm toolchain and open a PR (automation may do this).

Notes

  • Tools needed: curl, jq, base64, xxd, node, npm, and pnpm/corepack. Install if missing.
  • Keep edits minimal and readable—prefer explicit file edits over global replacements.
  • GitHub Actions must stay pinned to commit SHAs, not tags. Use the latest release tag only to discover the commit SHA to pin.
  • If GitHub API is rate-limited, retry with a token or bail out rather than guessing the tag.

FAQ

What does the pnpm-upgrade skill do?

Keep pnpm current: preflight the published package and pnpm/action-setup self-installer, update pnpm locally, align packageManager in package.json, and refresh CI pins. Use this when refreshing the pnpm toolchain manually or in automation.

How do I install pnpm-upgrade?

Run npx skills add https://github.com/openai/openai-agents-js --skill pnpm-upgrade in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/pnpm-upgrade/ (personal) or .claude/skills/pnpm-upgrade/ (project).

Which AI agents can use pnpm-upgrade?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is pnpm-upgrade safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains pnpm-upgrade?

It is published by openai in openai/openai-agents-js, and it is an official skill from the maker of the technology it covers. It has 143 recorded installs.

More from openai/openai-agents-js

View all →

docs-sync

openai/openai-agents-js

Audit or update authored English SDK documentation within a requested topic or diff using implementation evidence.

OfficialDocs & Writing147 installs

code-change-verification

openai/openai-agents-js

Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review.

OfficialAI & Agents139 installs

test-coverage-improver

openai/openai-agents-js

Measure JS SDK coverage or address measured coverage gaps. Use for coverage audits and metric regressions, not routine test additions.

OfficialTesting & QA132 installs

openai-knowledge

openai/openai-agents-js

Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence.

OfficialAI & Agents130 installs

pr-draft-summary

openai/openai-agents-js

Prepare a local PR title, description, and branch suggestion when requested or after eligible implementation work.

OfficialCode Quality & Workflow129 installs

changeset-validation

openai/openai-agents-js

Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.

OfficialAI & Agents127 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs