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/remix-run/react-router/implement-rfcnpx skills add remix-run/react-router --skill implement-rfcgit clone --depth 1 https://github.com/remix-run/react-routerWhat 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 | $0.00049 | $0.02036 |
| Opus 5 | $0.00024 | $0.01018 |
| Sonnet 5 | $0.00010 | $0.00407 |
| Haiku 4.5 | $0.00005 | $0.00204 |
Grade A, and why
implement-rfc 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement React Router RFC
Implement the RFC from the following GitHub discussion: $ARGUMENTS
Branching
RFC implementations should start from a clean working tree. If there are uncommitted changes, stop and ask me to resolve them before continuing.
- If you are already on a named branch that is at the same HEAD as
main, use that branch. - Otherwise, create a branch from
mainusing the format{author}/rfc-{semantic-name}:git branch {author}/rfc-{semantic-name} main git checkout {author}/rfc-{semantic-name}
Workflow
1. Fetch and Understand the RFC
Use WebFetch to read the discussion URL. If a GitHub discussion number is given instead of a URL, construct:
https://github.com/remix-run/react-router/discussions/<number>
Extract:
-
Problem being solved: what pain point does this RFC address?
-
Proposed API: exact function signatures, hook names, types, option shapes
-
Affected modes: Declarative / Data / Framework / RSC Data / RSC Framework
-
Breaking changes: does this change or remove existing public API?
-
Open questions: anything explicitly marked as unresolved, "TBD", or asked as a question in the proposal
-
Status: are there linked tracking issues? Look for links to other github issues and read them to see if there is additional context.
gh issue view <number> --repo remix-run/react-router
2. Evaluate Community Feedback
Fetch all comments from the discussion:
Use WebFetch on https://github.com/remix-run/react-router/discussions/<number> and scroll through the full thread. Look for:
- Concerns or objections raised by community members or maintainers
- Alternative proposals or API shape suggestions
- Edge cases raised that the proposal does not address
- Positive signals — repeated praise for a specific approach signals it's the right direction
- Maintainer responses — Ryan Florence, Michael Jackson, or other core team members clarifying intent
Summarize the community sentiment into:
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 · 240 lines · 49 tokens per session scan A 31de2d9d89e3
implement-rfc is a skill published in the GitHub repository remix-run/react-router (56,575 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 2,036 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.