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 jianzhichun/emerge --skill judge-promote-flywheelgit clone --depth 1 https://github.com/jianzhichun/emergeWrote 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/jianzhichun/emerge/judge-promote-flywheel)<a href="https://agentmods.dev/skills/jianzhichun/emerge/judge-promote-flywheel"><img src="https://agentmods.dev/badge/skills/jianzhichun/emerge/judge-promote-flywheel/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/jianzhichun/emerge/judge-promote-flywheel"><img src="https://agentmods.dev/badge/skills/jianzhichun/emerge/judge-promote-flywheel.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 | $0.00032 | $0.00232 |
| Opus 5 | $0.00016 | $0.00116 |
| Sonnet 5 | $0.00006 | $0.00046 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
judge-promote-flywheel 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 12d 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
Judge Promote Flywheel
Use this when evidence_applied is visible. The registry stores facts; Claude evaluates whether they are enough for a requested transition.
Workflow
- Read the intent's current registry entry and recent transition history.
- Inspect success rate, verify rate, human fixes, bridge failures, and recent outcomes.
- Compare the evidence with connector-local risk notes.
- If promotion is justified, call the explicit stage mechanism tool provided by the runtime.
- If not justified, leave state unchanged and explain the missing evidence.
Rules
- Never edit
intents.jsondirectly. - Treat silent-empty bridge regressions as safety failures.
- Reads can tolerate smaller blast radius than irreversible writes, but evidence still must be real.
- This skill is guidance only until the runtime exposes an approved explicit stage transition tool.
Output
Return the recommended target stage or no_change, evidence reviewed, and the safety rationale.
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.
- 12d ago First seen · 28 lines · 32 tokens per session scan A 0f161488b03f
judge-promote-flywheel is a skill published in the GitHub repository jianzhichun/emerge (107 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 232 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…