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 skillmds/skillmd --skill refine-livegit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/refine-live)<a href="https://agentmods.dev/skills/skillmds/skillmd/refine-live"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/refine-live/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/skillmds/skillmd/refine-live"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/refine-live.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 | $0.00103 | $0.06328 |
| Opus 5.5 | $0.00041 | $0.02531 |
| Sonnet 5.5 | $0.00021 | $0.01266 |
| Haiku 4.5 | $0.00010 | $0.00633 |
Grade A, and why
refine-live scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://localhost:7331/poller/start How it starts
The opening of the file, as written. The whole thing — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine Live
Two modes
Persistent (recommended — run and forget)
Run npx transitions-refine live from your project. The CLI starts the relay and wires REFINE_AGENT_CMD so the relay spawns your agent CLI per Refine click. No chat loop; idle = zero credit burn. Works hours later as long as the relay process keeps running. Stop with Ctrl-C (or npx transitions-refine stop).
In-chat loop (fallback — this skill)
Run /refine live in Cursor/Claude/Codex when the relay is up but has no REFINE_AGENT_CMD. You become the poller via GET /jobs/next. The Agent tab stays available only while you keep polling — each idle poll cycle consumes chat turns/credits. Say "stop refine" to exit.
Use the in-chat loop only when you cannot wire a persistent agent CLI.
Turn yourself into the LLM behind the Timeline Inspector's Refine button (in-chat fallback mode). While this loop runs, the panel's LLM tab is "available": each click sends one transition here, you reason about it, and your suggestions appear in the panel.
You are the poller. Nothing is installed — you just talk to a small local relay
(default http://localhost:7331) that the npx injector already started.
How it works
Browser (Refine, LLM tab) ──POST /jobs──► relay ──GET /jobs/next──► YOU
◄──GET /jobs/:id── relay ◄──POST /jobs/:id/result── YOU
The loop — stay live, but don't burn credits forever
Keep polling so the panel's LLM tab stays "available", but this loop costs chat turns/credits even while idle, so it is not truly run-and-forget — it has three exits, in priority order:
- Relay stop signal (authoritative).
GET /jobs/nextmay return200with{"stop": true}. The relay sends this when the user clicks Stop in the panel, or automatically after ~10 min with no jobs. Always honor it: stop looping immediately, tell the user the LLM tab will go unavailable and how to resume (/refine live), and end your turn. Never re-poll after a stop signal. - The user says so — "stop refine", "exit live", etc.
- Your own idle backoff (safety net). A long stretch of
204s is normal — it just means no one has clicked Refine yet — but to avoid spending credits on a forgotten loop, back off as idle grows instead of hammering immediately: re-poll right away for the first few empty cycles, then pause ~5s between polls, and after ~10 min of unbroken idle stop on your own (same as the relay's auto-stop) and tell the user how to resume. Any real job resets the backoff.
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.
- 1mo ago First seen · 451 lines · 103 tokens per session scan A 88aaeea58011
refine-live is a skill published in the GitHub repository skillmds/skillmd (143 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 6,328 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
refine-live compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| refine-liveskillmds/skillmd | Skill | 143 | 4d ago | MIT | A | 103 | Claude Code |
| sloplessberelevant-ai/slopless | Skill | 339 | 3d ago | MIT | A | 40 | Claude Code, Codex |
| suikonwiizo/suiko | Skill | 115 | yesterday | MIT | A | 192 | Codex |
| poly-lint-and-formatGoldziher/poly | Skill | 20 | today | MIT | A | 42 | Claude Code |
| poly-orchestratorGoldziher/poly | Skill | 20 | today | MIT | A | 43 | Claude Code |
| poly-mcpGoldziher/poly | Skill | 20 | today | MIT | A | 38 | Claude Code |
| poly-tiers-and-scopeGoldziher/poly | Skill | 20 | today | MIT | A | 60 | Claude Code |