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/changeset-prnpx skills add module-federation/core --skill changeset-prgit 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 | $0.00088 | $0.01072 |
| Opus 5 | $0.00044 | $0.00536 |
| Sonnet 5 | $0.00018 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
changeset-pr 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changeset PR
Overview
Create a repo-correct changeset for the current branch, or update an existing one without widening scope unnecessarily. Verify both syntax and package scope before handoff.
Ground the changeset in the live branch diff, not stale branch intent. Always inspect the current branch state against its base before choosing package scope or release type.
Workflow
- Confirm whether a changeset is needed.
- Identify the publishable package scope from the live branch diff.
- Create or edit one
.changeset/*.mdfile. - Validate the file against repo config and branch scope.
- Report the exact commands run and any ambiguity that remains.
Decide Whether A Changeset Is Needed
- Add a changeset when a publishable package behavior changes.
- Do not add one for docs-only or non-behavioral repo changes unless the user explicitly wants release metadata anyway.
- If unsure whether the change is user-visible enough to merit a release note, inspect existing changesets in
.changeset/and bias toward a short patch changeset rather than skipping silently.
Read references/repo-conventions.md when you need the repo-specific fixed-group, ignore-list, or release-flow details.
Determine Scope
First inspect the live branch state:
git diff --name-status origin/main...HEAD
git diff --stat origin/main...HEAD
git log --oneline --decorate --no-merges origin/main..HEAD
Use that to separate real publishable-package behavior changes from repo-local docs, skills, tooling, or cleanup.
Start with the helper script:
python3 .codex/skills/changeset-pr/scripts/inspect_changeset_scope.py --base origin/main
Use its output to separate:
- touched publishable packages
- ignored packages
- fixed groups that will affect release planning
If the branch touches multiple publishable packages, include only the packages whose behavior actually changed. Do not add app/example packages from the ignore list.
What ships with it
4 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.
- yesterday First seen · 132 lines · 88 tokens per session scan A db4e918b1817
changeset-pr is a skill published in the GitHub repository module-federation/core (2,625 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,072 once invoked, about $0.0004 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
nextjs-app-router
Full end-to-end tRPC setup for Next.js App Router. Covers route handler with fetchRequestHandler (GET + POST exports), TRPCProvider with QueryClientProvider, createTRPCOptionsProxy for RSC prefetching, HydrateClient/HydrationBoundary for hydration, useSuspenseQuery for Suspense, and server-side callers.
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
openapi
Generate OpenAPI 3.1 spec from a tRPC router with @trpc/openapi CLI or programmatic API. Generate typed REST client with @hey-api/openapi-ts and configureTRPCHeyApiClient(). Configure transformers (superjson, EJSON) for generated clients. Alpha status.
server-setup
Initialize tRPC with initTRPC.create(), define routers with t.router(), create procedures with .query()/.mutation()/.subscription(), configure context with createContext(), export AppRouter type, merge routers with t.mergeRouters(), lazy-load routers with lazy().
subscriptions
Set up real-time event streams with async generator subscriptions using .subscription(async function() { yield }). SSE via httpSubscriptionLink is recommended over WebSocket. Use tracked(id, data) from @trpc/server for reconnection recovery with lastEventId. WebSocket via wsLink and createWSClient from @trpc/client…
react-query-setup
Set up @trpc/tanstack-react-query with createTRPCContext(), TRPCProvider, useTRPC() hook, queryOptions/mutationOptions factories, query invalidation via queryClient.invalidateQueries with queryFilter, and type inference with inferInput/inferOutput.