Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add zjunlp/Mechanist/plugin install mechanistWrote 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/zjunlp/mechanist/idea-creator)<a href="https://agentmods.dev/skills/zjunlp/mechanist/idea-creator"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/idea-creator.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 5.1 | $0.00047 | $0.03069 |
| Opus 5 | $0.00023 | $0.01535 |
| Sonnet 5 | $0.00009 | $0.00614 |
| Haiku 4.5 | $0.00005 | $0.00307 |
Grade A, and why
idea-creator 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 6d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Idea Creator
Generate publishable research ideas for: $ARGUMENTS
Overview
Given a broad research direction from the user, systematically generate, validate, and rank concrete research ideas. This skill composes with /research-lit, /novelty-check, and /research-review to form a complete idea discovery pipeline.
Constants
- PILOT_MAX_HOURS = 4 — Skip any pilot estimated to take > 4 hours per GPU. Flag as "needs manual pilot".
- PILOT_TIMEOUT_HOURS = 6 — Hard timeout: kill pilots exceeding 6 hours. Collect partial results if available.
- MAX_PILOT_IDEAS = 6 — Pilot at most 6 ideas in parallel. Additional ideas are validated on paper only.
- MAX_TOTAL_GPU_HOURS = 10 — Total GPU budget for all pilots combined.
- REVIEWER_BACKEND =
llm-chat— External LLM reviewer via llm-chat MCP for brainstorming (Phase 2 idea generation) and review (Phase 4 devil's-advocate critique). Model defers toLLM_MODELenv. Always ask the external reviewer for strict, high-rigor feedback. Override with— reviewer: oracle-provia Oracle MCP. - OUTPUT_DIR =
idea-stage/— All idea-stage outputs go here. Create the directory if it doesn't exist.
💡 Override via argument, e.g.,
/idea-creator "topic" — pilot budget: 4h per idea, 20h total.
Workflow
Phase 1: Load Landscape + Banlist (produced by /research-lit)
Division of labor.
/research-litis the canonical owner of the landscape and banlist. Its Step 0 reads any existing prior banlist and its Step 5 synthesizes everything intoidea-stage/LANDSCAPE.md— paper table + 3-5 paragraph narrative + structural gaps + a## 5. Banlist — Failed Ideassection. This skill does not survey the literature; it consumes that file.
Path A — auto-claim chain (the normal path).
If idea-stage/LANDSCAPE.md exists non-empty, Read it. Treat it as the canonical landscape, and treat its ## 5. Banlist — Failed Ideas section as ideas NOT to regenerate. Do not re-survey. This is the explicit auditable source and avoids drift if an in-context survey would later be summarized away in a long session.
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.
- 6d ago First seen · 237 lines · 47 tokens per session scan A 29c767717673
idea-creator is a skill published in the GitHub repository zjunlp/Mechanist (55 stars, last pushed 10d ago), licensed MIT. It adds 47 tokens to every session and 3,069 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
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
nanoresearch-planning
Produce an experiment blueprint from a research hypothesis.
nanoresearch-ideation
Search academic literature and generate research hypotheses.
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.