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 agentmods add skills/module-federation/core/local-cinpx skills add module-federation/core --skill local-cigit clone --depth 1 https://github.com/module-federation/coreWhat 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 | $0.00068 | $0.00857 |
| Opus 5 | $0.00034 | $0.00428 |
| Sonnet 5 | $0.00014 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
local-ci 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local CI
Use the local CI runner and Turbo/package scripts as the source of truth for validation in this repo.
Quick Start
- Start with the smallest deterministic check that matches the change.
- Prefer
pnpm run ci:local --only=<job>for CI-parity validation. - Prefer direct Turbo or package scripts only when they are the smaller equivalent of the CI job.
- Report exactly which command ran, what failed first, and which expected checks were skipped.
Workflow
1. Inspect available local CI jobs
Run:
pnpm run ci:local --list
Use this when the right job is unclear or when the repo may have added or renamed jobs.
For the current job map, read references/jobs.md.
2. Pick the smallest matching job
Use these defaults:
- Package code in
packages/*: start withbuild-and-testonly if the change is broad; otherwise prefer package build/test commands. - Metro packages or Metro workflow changes: use
build-metro, then Metro E2E jobs only if relevant. - E2E app changes: run the matching
e2e-*job instead ofbuild-and-test. - Devtools workflow or Playwright/devtools changes: run
devtools. - Bundle-size workflow/reporting changes: run
bundle-size. - GitHub workflow syntax only: use
actionlintlocally only to see skip behavior; the actual action is CI-only. - Broad CI, packaging, publint, Turbo, or shared runtime changes: run
build-and-test.
3. Run commands in CI order
When reproducing CI, use the same command shape as the repo:
pnpm run ci:local --only=build-and-test
pnpm run ci:local --only=devtools
pnpm run ci:local --only=e2e-runtime
To run more than one job:
pnpm run ci:local --only=build-and-test,bundle-size
4. Interpret failures correctly
- Treat the first failing step as the actionable failure.
- Ignore known noisy warnings unless they exit non-zero.
- Distinguish repo-wide drift from changed-file gates.
- If
ci:localfails inCheck code format, inspect the changed-file formatter result before running broader builds. - If a dependency build outside the touched scope fails, note it separately as an unrelated blocker.
What ships with it
2 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 · 104 lines · 68 tokens per session scan A bbf5334f437e
local-ci is a skill published in the GitHub repository module-federation/core (2,625 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 857 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
deploy-release-test
Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the teste2edeployrelease.yml GitHub Actions workflow. Use only when asked to run the full deploy test suite or this workflow specifically from an internal vercel/next.js PR branch. Do not use for…
ci-workflow-sync
FastGPT CI workflow 双轨同步。当用户修改或新增 .github/workflows/ 下的 GitHub Actions workflow 时必须触发：同步更新 .forgejo/workflows/ 对应文件保持功能一致，或判断是否需要新建 Forgejo 版本。涉及 CI、GitHub Actions、Forgejo Actions、镜像构建、container registry、artifact、workflow yaml 改动、build- workflow、test- workflow 时也使用此技能。即使用户只提到"改一下 CI"或"加个 workflow"也应触发。.
vercel-deploy
Deploy applications to Vercel with edge functions, serverless, and ISR.
saas-deployment
SaaS uygulamasını production'a taşı. Vercel, Railway veya Fly.io ile deployment, domain yapılandırması, SSL, ortam değişkenleri, CI/CD, izleme ve operasyonel hazırlık. Bu skill'i kullanıcı deploy, yayınlama, production, hosting, domain, SSL, CI/CD, monitoring veya "siteyi canlıya al" ile ilgili bir şey istediğinde…
verify-github-workflows
GitHub Actions, labeler, CODEOWNERS, PR template 변경 후 trigger, permission, concurrency, secret 노출을 검증할 때 사용합니다.
playwright-ci-caching
Cache Playwright browser binaries in CI/CD pipelines (GitHub Actions, Azure DevOps) to avoid 1-2 minute download overhead on every build.