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 skills add jschulte/claude-plugins --skill finish-linegit clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/jschulte/claude-plugins/finish-line)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/finish-line"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/finish-line/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/jschulte/claude-plugins/finish-line"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/finish-line.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 | $0.00063 | $0.02552 |
| Opus 5.5 | $0.00025 | $0.01021 |
| Sonnet 5.5 | $0.00013 | $0.00510 |
| Haiku 4.5 | $0.00006 | $0.00255 |
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 24d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finish Line
Use the user's intended experience as the destination and the actual repository as the starting point. Assess or propose an architecture that makes the product correct, reliable, scalable and easier to understand and change. The intended benefits are lower maintenance burden, faster safe fixes/features, and fewer competing implementations. Reuse sound existing work; add capabilities in service of the agreed product outcome.
Default deliverable and depth
Default to a rigorous assessment and a proposed medium-level product and architecture roadmap for discussion. Begin with the whole system's structure after establishing its purpose. Explain the problems, affected users, practical corrections, shared responsibilities to reuse, and observable finished behavior. Investigate deeply enough to support those judgments; present them concisely.
Capture the user's narrative, signature interaction and constraints, not just a feature list. Translate them into the shortest meaningful successful journey and the outcomes the product must deliver. A requested immediate capture experience, for example, must survive architectural planning as an observable interaction requirement. Distinguish requested outcomes from inferred opportunities; do not turn an illustrative example into a universal requirement.
Keep two levels distinct:
- Assessment and roadmap: explain the intended destination, cover the requested system, cross-area consolidations, existing work, priorities and acceptance outcomes. Present unsettled scope as a proposal. Future work may be well understood without exact interfaces, file reservations or test scripts.
- Specs and implementation handoffs: after the direction is agreed and this detail is requested, specify the next selected chunks—ordinarily one to three unless the user chooses another scope. Expand later chunks when selected and recheck their then-current source and owners.
A request to review the whole platform, be thorough, or explain what needs fixing does not by itself request an exhaustive implementation specification. Do not generate a packet for every finding or section, fill a template's optional fields, or keep writing distant specs to make a roadmap look complete. Explicit requests for broader implementation planning override this default.
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.
- 24d ago First seen · 91 lines · 63 tokens per session scan A 23141b957fa2
finish-line is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 63 tokens to every session and 2,552 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…