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 joao-aires/agent-skills-public --skill refinegit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/refine)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/refine"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/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/joao-aires/agent-skills-public/refine"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/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 | $0.00046 | $0.00702 |
| Opus 5.5 | $0.00018 | $0.00281 |
| Sonnet 5.5 | $0.00009 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
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 yesterday.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine
Read task guidance. Read project-conventions for affected project constraints. Load the optional stack/domain guidance selected by task guidance only when relevant and available.
Establish the change
Read the request alongside the code or documentation for the behavior being changed. Trace how the user reaches that behavior, what the application does today, and where the requested result differs. This gives the refinement a concrete starting point and often answers questions that would otherwise be sent back to the user.
Describe the change in the user's terms: who needs to do what, why the present behavior is insufficient, and what a successful result would let them do. Include the parts of the experience that must remain unchanged. Where the request names a solution, establish which need that solution is intended to satisfy before treating every suggested detail as a requirement.
Resolve implementation facts from the repository. Ask the user about choices only they can settle, such as which users may perform an action or whether an existing behavior should change. For a reversible assumption, say what you are assuming and which part of the result depends on it.
If the problem or product priority is still unresolved, use installed product discovery and prioritization expertise to shape that decision within scope before detailing the change. Accepted product context needs no new discovery cycle.
Define actionable work
Write requirements that another contributor could implement without reconstructing the conversation. Connect each important requirement to an observable result:
- Describe the action, the conditions in which it is available, and the resulting visible or stored state.
- Explain what happens when the action is denied, cannot finish, or is attempted again, where those cases affect the requested behavior.
- Identify the screens, APIs, stored data and external consumers that need to agree about the change. Name existing behavior that constrains compatibility.
- Describe how the result will be checked. Choose a check that observes the promised result, rather than merely showing that a function was called.
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.
- yesterday Changed · +24 lines 654a9d6af883
- 2d ago Changed · +2 lines 744892b0c976
- 7d ago First seen · 24 lines · 46 tokens per session scan A dc5f13c8cd3e
refine is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 702 once invoked, about $0.0002 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 2026-10-15.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…