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 woliveiras/geremmyas --skill refinegit clone --depth 1 https://github.com/woliveiras/geremmyasWrote 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/woliveiras/geremmyas/refine)<a href="https://agentmods.dev/skills/woliveiras/geremmyas/refine"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/refine/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/woliveiras/geremmyas/refine"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/refine.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 | $0.00035 | $0.00555 |
| Opus 5 | $0.00017 | $0.00278 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
refine 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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine
Reach shared understanding before writing PRDs, specs, plans, or tasks. For the full stop conditions, see readiness and authority boundaries.
Process
- Explore the relevant code, docs, specs, PRDs,
GLOSSARY.md,CONTEXT.md, and ADRs before asking questions. - Classify the work:
- new feature
- existing feature expansion
- bugfix
- refactor
- documentation/setup
- For existing features, decide whether the product flow changes. If it does, update the PRD before writing specs. If it does not, write targeted specs. If a PRD exists without a spec, do not proceed to implementation until a spec is written from the PRD.
- Ask one focused question at a time. For each question, include a recommended answer based on the codebase and documents.
- Challenge vague or overloaded terms and propose canonical vocabulary.
- Record resolved decisions in the right artifact: PRD, spec, ADR, or
tasks.md. - Record explicit session overrides such as read-only, plan-only, no-edits, or no-commits. These overrides take precedence over the autonomous workflow.
- When the objective is clear, let
speccreate and validate the durable artifacts without adding a conversational approval pause.
Rules
- Local atomic commits are the default after a verified slice. Omit conversational permission and file, hunk, or message selection prompts.
- A read-only, plan-only, no-edits, or no-commits override disables commits for the session. Report changed or proposed files at the commit boundary. Commit authority never implies push or production authority.
- Do not ask questions that code or existing docs can answer.
- Do not write a spec until the key branches of the decision tree are resolved.
- Infer decisions from repository conventions when the choice is reversible and record the inference in the relevant artifact.
- Escalate a feature before implementation only when blast radius is high and at least one of these is true: rollback is unproven, or critical harness evidence is missing. Product ambiguity that materially changes the objective still requires clarification.
- Do not create an ADR unless the decision is complex, hard to reverse, surprising without context, and based on a real trade-off.
What ships with it
1 file 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.
- 10d ago First seen · 54 lines · 35 tokens per session scan A 0570051125bc
refine is a skill published in the GitHub repository woliveiras/geremmyas (10 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 555 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…