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 runner-elicitation-policygit 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/runner-elicitation-policy)<a href="https://agentmods.dev/skills/jianzhichun/emerge/runner-elicitation-policy"><img src="https://agentmods.dev/badge/skills/jianzhichun/emerge/runner-elicitation-policy/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/runner-elicitation-policy"><img src="https://agentmods.dev/badge/skills/jianzhichun/emerge/runner-elicitation-policy.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 | $0.00035 | $0.00302 |
| Opus 5 | $0.00017 | $0.00151 |
| Sonnet 5 | $0.00007 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
runner-elicitation-policy 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
Runner Elicitation Policy
Purpose
Runner popups are scarce attention. Use them only when operator input changes the outcome and the system cannot safely proceed from existing evidence.
Interrupt Only When
- The intent is ambiguous and a wrong choice would create or reinforce the wrong pipeline.
- The action is irreversible or high risk and cannot be recovered by rollback.
- A local preference is needed to interpret repeated behavior, such as a target layer or naming convention.
Do Not Interrupt For
- Started, running, completed, or routine failure notifications.
- Read-only status, health, or sync updates.
- Errors the daemon can retry or classify without user input.
- Asking the operator to approve a pipeline that policy already promoted.
Popup Copy
- State the decision in one sentence.
- Offer concrete choices, not open-ended explanation requests.
- Include a default only when timeout behavior is safe.
- Mention the affected connector/profile when it prevents ambiguity.
Failure Classes
timeout: no operator answer; record as no decision, not rejection.dismissed: operator intentionally declined interruption; do not repeat immediately.upload_failed: transport issue; retry if the decision is still relevant.render_failed: local UI unavailable; fall back to event stream and avoid loops.
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 · 38 lines · 35 tokens per session scan A da4d2f785f3b
runner-elicitation-policy is a skill published in the GitHub repository jianzhichun/emerge (107 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 302 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…