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 agentmods add skills/ondrasek/cc-plugins/refinenpx skills add ondrasek/cc-plugins --skill refinegit clone --depth 1 https://github.com/ondrasek/cc-pluginsWhat 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 | $0.00030 | $0.01839 |
| Opus 5 | $0.00015 | $0.00920 |
| Sonnet 5 | $0.00006 | $0.00368 |
| Haiku 4.5 | $0.00003 | $0.00184 |
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 2d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine
Transforms rough or incomplete issues into well-structured epics and user stories using proven techniques.
Critical Rules
- Read cross-cutting behaviors first:
skills/shared/references/cross-cutting.md - Always read the current issue content before refining — never assume
- Ask clarifying questions when information is missing — don't guess at requirements
- Preview all changes with the user before updating the issue
- Add a refinement comment to every refined issue explaining what changed
- NEVER create priority labels — see
skills/shared/references/label-taxonomy.md - Use GitHub sub-issues for epic decomposition (not task-list checkboxes)
Prerequisites Check
gh auth status
Reference Files
Read these on demand based on the refinement type:
references/epic-guide.md— epic structure, scope definition, decomposition heuristicsreferences/user-story-guide.md— user story format, INVEST criteria, acceptance criteria patternsreferences/splitting-techniques.md— 9 SPIDR techniques for breaking down stories
Capabilities
1. Refine to User Story
Take a rough or empty issue and refine it into a well-structured user story.
Workflow:
-
Read the issue:
gh issue view NUMBER --json number,title,body,labels,assignees,comments -
Assess completeness — identify what's missing:
- Who is the user/persona?
- What do they want to achieve?
- Why does it matter (business value)?
- What are the boundaries (in-scope vs out-of-scope)?
- What does "done" look like?
-
Ask clarifying questions — present gaps to the user and ask for input. Do not fabricate requirements.
-
Draft the refined issue body (read
references/user-story-guide.mdfor format):- User story statement: "As a [user], I want [goal], so that [benefit]"
- Context and background
- Acceptance criteria (Given/When/Then or checklist)
- Out of scope (explicitly state what this does NOT cover)
- Technical notes (if relevant)
- Related issues (from cross-cutting search)
What ships with it
3 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.
- 2d ago First seen · 212 lines · 30 tokens per session scan A aeb4102deb58
refine is a skill published in the GitHub repository ondrasek/cc-plugins (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,839 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…