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 zjunlp/Mechanist --skill impact-checkgit clone --depth 1 https://github.com/zjunlp/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/impact-check)<a href="https://agentmods.dev/skills/zjunlp/mechanist/impact-check"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/impact-check.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01027 |
| Opus 5 | $0.00022 | $0.00513 |
| Sonnet 5 | $0.00009 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
impact-check 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 8d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impact Check Skill
Check whether a proposed idea studies an important problem/behavior — one worth committing effort to: $ARGUMENTS
What Counts as Impact
An idea is high-impact to the extent it does ANY of the following:
- solves an important problem;
- is likely to be widely used or cited by follow-up research;
- could change the direction of a research area;
- helps real applications, industry, society, or cross-disciplinary research;
- reveals an important phenomenon, even if the method is simple.
Constants
- REVIEWER_BACKEND =
llm-chat— External LLM reviewer via llm-chat MCP (model defers toLLM_MODELenv). Always ask the external reviewer for strict, high-rigor feedback.
Instructions
Given an idea / behavior description, systematically assess its importance:
Phase A: Extract the Impact-Bearing Claims
- Read the description and name the behavior/phenomenon or problem under study (not the method).
- Extract the elements that determine its importance:
- What problem does it address, and who actually has that problem?
- What downstream research or applications would build on it if the result holds?
- What would change — in the field or in practice — if it is true?
- What is the reach: one narrow setting, a whole research area, or real-world / cross-disciplinary use?
- State the single strongest one-line case for why it matters.
Phase B: Assess Impact Along the Dimensions
For EACH impact dimension below, judge how strongly the idea scores and gather supporting evidence (use WebSearch / WebFetch to check whether the problem is an open/active question, how much attention it gets, and where it would be used):
- Important problem — Is this a problem the field (or a real application) actually needs solved, or a niche curiosity?
- Uptake / citation — Would follow-up research likely build on, use, or cite this? Does it produce a reusable artifact (dataset, method, finding, diagnostic)?
- Direction-shifting — Could the result change how people think about or approach a research area?
- Real-world reach — Does it help applications, industry, society, or cross-disciplinary work?
- Phenomenon value — Even if the method is simple, does the result reveal an important phenomenon?
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.
- 8d ago First seen · 87 lines · 44 tokens per session scan A 3a68c8eeca5f
impact-check is a skill published in the GitHub repository zjunlp/Mechanist (72 stars, last pushed 12d ago), licensed MIT. It adds 44 tokens to every session and 1,027 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-writing
Draft a LaTeX research paper from all previous stage outputs.
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint.
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.