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.
git clone --depth 1 https://github.com/juanmhidalgo/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/commands/juanmhidalgo/claude-plugins/refine)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/refine"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/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/commands/juanmhidalgo/claude-plugins/refine"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/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 | $0.00039 | $0.00528 |
| Opus 5 | $0.00019 | $0.00264 |
| Sonnet 5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
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 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.
What it actually says
Input to Refine
$ARGUMENTS
Instructions
Use the Agent tool to invoke the prd-specialist agent to refine or convert the input to a proper PRD.
The agent should:
-
Load the content from one of these sources:
- Local file path (e.g.,
./docs/prd-auth.md) - GitHub issue URL (e.g.,
https://github.com/owner/repo/issues/123) - If argument is "paste" or empty, ask user to paste the content
- Local file path (e.g.,
-
Detect content type:
- Already a PRD: Has structured sections (Overview, Goals, Acceptance Criteria, etc.)
- Vague issue: Unstructured text, feature request, or bug description
-
If already a PRD - Analyze and improve:
- Are acceptance criteria observable (not implementation details)?
- Are user stories from user perspective?
- Is Out of Scope defined?
- Are goals measurable?
- Provide specific feedback and suggested rewrites
-
If vague issue - Convert to PRD:
- Extract the core problem/request
- Ask 1-2 clarifying questions if needed
- Generate full PRD structure
- Preserve original context and intent
-
Offer to apply changes:
- Update the file directly
- Update the GitHub issue
- Display the improved/converted version
Keep the collaborative tone - iterate based on user feedback.
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.
- 6d ago First seen · 66 lines · 39 tokens per session scan A ed4714116cbd
refine is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 528 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 2026-09-03.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.