finish-line

finish-line is a skill for Claude Code from remix-run/react-router. It costs 82 tokens per session (1,204 once invoked), scanned A, original, MIT.

A workflow for completing blocked community pull requests in the React Router project. A pull request is a proposed code change sent for review, and merge blockers are issues that prevent it from being accepted.

In plain words
What is it for?
Inspecting a React Router pull request, checking its reviews and automated checks, adding maintainer-owned files when appropriate, and resolving merge blockers.
Why use it?
It identifies whether the remaining work involves tests, documentation, change notes, or contributor follow-up. It preserves contributor ownership and avoids overwriting unrelated local changes.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: installed under .agents/ (shared by several agents); mentions Codex; $skill-name invocation.

About the project

React Router is a routing system for React applications that maps URLs to the interface shown on screen. Developers use it either as a small library within their own application structure or as part of a full React framework.

remix-run/react-router · 56,578 stars · on GitHub · reactrouter.com

Install

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.

agentmods
npx agentmods add skills/remix-run/react-router/finish-line
Any agent
npx skills add remix-run/react-router --skill finish-line
Clone the repo
git clone --depth 1 https://github.com/remix-run/react-router

Made for: Claude Code.

Wrote 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.

agentmods badge for finish-line

README.md
[![agentmods](https://agentmods.dev/badge/skills/remix-run/react-router/finish-line.svg)](https://agentmods.dev/skills/remix-run/react-router/finish-line)
Your own site
<a href="https://agentmods.dev/skills/remix-run/react-router/finish-line"><img src="https://agentmods.dev/badge/skills/remix-run/react-router/finish-line.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.01204
Opus 5 $0.00041 $0.00602
Sonnet 5 $0.00016 $0.00241
Haiku 4.5 $0.00008 $0.00120

Measured 6d ago against content hash 77e096abdb98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

finish-line 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 6d 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.

.agents/skills/finish-line/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finish Line

Overview

Finish blocked community PRs in remix-run/react-router while respecting contributor ownership and the repo's PR packaging conventions.

Treat the PR number or URL in $ARGUMENTS as the target PR. If no target is provided, ask for it before doing anything.

Triage

  1. Inspect local state with git status --short --branch. If unrelated dirty files exist, do not overwrite or stage them.
  2. Fetch current main before making branch decisions:
git fetch origin main
  1. Gather PR context:
gh pr view <pr> --repo remix-run/react-router --json number,title,body,state,isDraft,author,baseRefName,headRefName,headRepository,headRepositoryOwner,maintainerCanModify,mergeStateStatus,reviewDecision,labels,files,commits,statusCheckRollup,url
gh pr checks <pr> --repo remix-run/react-router
gh pr diff <pr> --repo remix-run/react-router --stat
gh pr view <pr> --repo remix-run/react-router --comments
  1. Identify merge blockers. In particular:
  • If the PR only needs repo-maintainer additions such as tests, a change file, or docs, use the contributor-branch workflow.
  • If the contributor branch cannot be modified, summarize the evidence and ask the user whether to wait for the contributor or recreate the work on a maintainer branch.
  • If the blocker is unclear, summarize the evidence and ask the user which path to take.
  1. Evaluate test coverage before deciding the finish-line changes:
    • Inspect the PR diff, changed files, existing nearby tests, review comments, and failed checks for test expectations.
    • If the PR changes runtime behavior, build/plugin behavior, routing semantics, generated types, RSC behavior, docs rendering, or any bug/feature surface that can regress, add or preserve a focused test unless equivalent coverage already exists.
    • If tests are already included, verify they exercise the changed behavior and cover the affected React Router mode(s): Declarative, Data, Framework, RSC Data, and/or RSC Framework.
    • If tests are not needed because the change is documentation-only, packaging-only, a change file, or otherwise not executable behavior, note that rationale in the final report.
    • If a useful test is required but too large or risky for the finish-line scope, stop and ask the user before broadening the PR.

Read the full file on GitHub · 106 lines

Changes

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.

  1. 6d ago First seen · 106 lines · 82 tokens per session scan A 77e096abdb98

Subscribe to this mod's changes

finish-line is a skill published in the GitHub repository remix-run/react-router (56,578 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 1,204 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens