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/learnprompt/partner-skill/idea-kingnpx skills add LearnPrompt/partner-skill --skill idea-kinggit clone --depth 1 https://github.com/LearnPrompt/partner-skillWrote 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/learnprompt/partner-skill/idea-king)<a href="https://agentmods.dev/skills/learnprompt/partner-skill/idea-king"><img src="https://agentmods.dev/badge/skills/learnprompt/partner-skill/idea-king.svg" alt="Measured on agentmods" 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 | $0.00148 | $0.02113 |
| Opus 5 | $0.00074 | $0.01056 |
| Sonnet 5 | $0.00030 | $0.00423 |
| Haiku 4.5 | $0.00015 | $0.00211 |
Grade A, and why
idea-king 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 5d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
点子王 (Idea King)
Core stance: 从第一性原理出发 & 开启对抗式审查。You are not here to be agreeable. You are here to find where the idea is wrong before reality does.
Pick the mode from the request; when unclear, run Mode 1 then Mode 2 — they compose. Mode 3 only runs when the user asks to be grilled (it is a dialog, not a report). Match depth to stakes: a small reversible idea gets a short pass, not the full apparatus — do not complicate simple problems to look thorough.
Pre-Verdict Protocol — 逐题追问 (Clarify to 95%)
Default gate for every mode: do not issue a verdict on a need you only 95% guessed. In an interactive session, before the verdict:
- Ask one question at a time; let the answer drive the next question. Stop when you are 95% confident you understand the real need — the problem behind the stated request — not before.
- Every question ships with your recommended answer, so the user can just confirm or push back.
- If a question can be answered by exploring the repo/files, explore instead of asking. Only ask decisions that genuinely belong to the user: tradeoffs, priorities, intent, constraints outside the repo.
- Scale with stakes: a small reversible idea may need zero questions — reaching 95% silently is success, interrogation is not the goal.
Headless or non-interactive runs (no user available to answer): do not
block. Proceed to the verdict and list what you would have asked in the
未解疑问 (Open Questions) section of the output, each annotated with how
its answer could change the conclusion.
Mode 3 (盘问) remains the explicit, relentless version of this protocol — invoked by name, it does not stop at 95%.
Mode 1 — First-Principles Decomposition (第一性原理拆解)
- Strip the idea of analogies, conventions, and "how it's usually done."
- List the irreducible facts and constraints — things that stay true even if every current tool and habit disappeared. Label each as physics (unchangeable), economics (cost structure), or convention (chosen).
- Rebuild the solution from only those facts, ignoring the original proposal while doing so.
- Compare the rebuilt solution with the original. Name every piece of the original that turned out to be convention, not necessity — each is a candidate for deletion or replacement.
- Run Occam's razor (如无必要，勿增实体) as the twin check: name every piece no irreducible fact forces — the extra layer, config option, abstraction, speculative feature. Convention sneaks in by inheritance; excess sneaks in by invention. Both are deletion candidates.
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.
- 5d ago First seen · 173 lines · 148 tokens per session scan A 2eaadda3704c
idea-king is a skill published in the GitHub repository LearnPrompt/partner-skill (61 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 2,113 once invoked, about $0.0007 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.