A requirements-clarification skill for product and technical work. It examines the project's existing code and documents before asking focused questions and recording the decisions.

Use it when starting a feature, expanding an existing feature, fixing a bug, or planning a refactor whose requirements are not yet precise.

It helps resolve vague or conflicting requirements before someone writes a specification or starts implementation. It also keeps the agreed terminology and decisions in the appropriate project documents.

refine — Skill for Claude Code and Codex by woliveiras/geremmyas

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.

Any agent

npx skills add woliveiras/geremmyas --skill refine

Clone the repo

git clone --depth 1 https://github.com/woliveiras/geremmyas

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/woliveiras/geremmyas/refine/github.svg)](https://agentmods.dev/skills/woliveiras/geremmyas/refine)

Your own site

<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.

Your own site · 80×15

<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>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 555 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00555
Opus 5.5	$0.00014	$0.00222
Sonnet 5.5	$0.00007	$0.00111
Haiku 4.5	$0.00003	$0.00056

Measured 2mo ago against content hash 0570051125bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

content/skills/refine/SKILL.md · 54 lines

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 spec create 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.

Read the full file on GitHub · 54 lines

Files

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.

references/readiness-and-authority.md 4.7 KB

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.

2mo ago First seen · 54 lines · 35 tokens per session scan A 0570051125bc

Subscribe to this mod's changes

refine is a skill published in the GitHub repository woliveiras/geremmyas (10 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 555 once invoked, about $0.0001 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 2026-08-31.

Planning

refine next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
refinewoliveiras/geremmyas	Skill	10	3mo ago	MIT	A	35	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code