GitHub Agentic Workflows is a GitHub CLI extension that lets developers define AI-assisted repository automation in Markdown and run it through GitHub Actions. It is intended for tasks requiring interpretation or reasoning, such as issue triage, pull-request review, CI investigation, documentation maintenance, and dependency analysis. The catalogue entries provide skills and agents for working with these workflows.
Borrowing it
Nothing to install: this file belongs to github/gh-aw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/github/gh-aw/main/.github/skills/npm/SKILL.mdgit clone --depth 1 https://github.com/github/gh-awWrote 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/github/gh-aw/npm)<a href="https://agentmods.dev/skills/github/gh-aw/npm"><img src="https://agentmods.dev/badge/skills/github/gh-aw/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/github/gh-aw/npm"><img src="https://agentmods.dev/badge/skills/github/gh-aw/npm.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 | $0.00029 | $0.00799 |
| Opus 5.5 | $0.00012 | $0.00320 |
| Sonnet 5.5 | $0.00006 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
npm scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Keep HTTPS and TLS verification enabled. Never use `strict-ssl=false`, `NODE_TLS_REJECT_UNAUTHORIZED=0`, `curl -k`, or an HTTP registry, and do not disconnect the VPN or bypass corporate network controls. Copies of this mod
1 near-identical copy found in the catalogue:
- npm — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
npm on the Microsoft network or VPN
Use this skill when npm downloads are blocked by the Microsoft corporate network or VPN. Run commands in the affected package directory. Prefer npm ci with the existing lockfile and default registry when access works; do not change dependency versions to solve a network failure.
Use the 1ES public npm feed
When access to npmjs is blocked, retry through the Microsoft 1ES public feed with command-scoped settings:
registry=https://ms-feed-25.pkgs.visualstudio.com/1es-public/_packaging/npm-public/npm/registry/
npm ci --registry="$registry" --replace-registry-host=npmjs
--replace-registry-host=npmjs routes npmjs lockfile downloads through the selected registry without rewriting the lockfile. Private registries and lifecycle scripts that download from other hosts still need their own approved network access. Do not edit manifests, lockfile URLs, or committed npm configuration just to work around the local VPN.
To diagnose feed access, query an actual package and exact version from the lockfile. For example, substitute the project's pinned package and version in:
npm view [email protected] version --registry="$registry" \
--fetch-retries=0 --fetch-timeout=15000
Use npm view, not npm ping: the feed may not implement the ping endpoint. A successful metadata query checks that package's availability, not tarball or postinstall access. Retry the original install to verify recovery.
If the feed returns an authentication error or lacks the pinned package, report the blocker rather than guessing credentials or trying arbitrary mirrors. Caching an upstream package can require feed permissions.
Proxy and certificate failures
The feed is an npm registry, not an HTTP proxy. Never set HTTPS_PROXY or HTTP_PROXY to the feed URL. If a forward proxy is required, use only an IT-approved proxy URL in the current shell and check NO_PROXY for unintended bypasses. Do not expose proxy credentials or copy machine-specific configuration into the repository or logs.
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.
- 13d ago First seen · 49 lines · 29 tokens per session scan A 8c5a13658b30
npm is a skill published in the GitHub repository github/gh-aw (5,406 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 799 once invoked, about $0.0001 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 2026-10-04.
Other skills, from other repositories
Flaky Test Doctor
Diagnose flaky test failures from Playwright reports, traces, and rerun history. Classify each failure as product, test, environment, data, or unknown with cited evidence and a proposed fix. Never auto-modifies code without opt-in.
GitHub CI Fix Debugging
Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.
fixing
Diagnose why a PR's CI failed — compare the CI definition against the sandbox, classify the failure, and make the minimal repair. Use when a PR is red and you must work out why before changing anything.
argot-refresh
Refresh Argot's committed fit snapshot safely — first diagnose why maintenance is recommended, re-audit corpus scope and structural path changes, review stale mutes and policy entries with the user, then fit locally, verify, and prepare the reviewed .argot/ update. Use when argot status, argot check, MCP, or CI…
Systematic Debugging
Reproduce a bug, isolate the cause, and fix it only after evidence identifies the failure path.
Error Analysis
Cluster failures and explain model or router error patterns.