Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zjunlp/Mechanistnpx agentmods add skills/zjunlp/mechanist/experiment-planWrote 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/experiment-plan)<a href="https://agentmods.dev/skills/zjunlp/mechanist/experiment-plan"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/experiment-plan.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 | $0.00080 | $0.02485 |
| Opus 5 | $0.00040 | $0.01242 |
| Sonnet 5 | $0.00016 | $0.00497 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade A, and why
experiment-plan 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 7d 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.
This is a copy
91% identical to experiment-plan — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Plan: Claim-Driven, Paper-Oriented Validation
Refine and concretize: $ARGUMENTS
Overview
Use this skill after the method is stable enough that the next question becomes: what exact experiments should we run, in what order, to defend the paper? If the user wants the full chain in one request, prefer /research-refine-pipeline.
The goal is not to generate a giant benchmark wishlist. The goal is to turn a proposal into a claim -> evidence -> run order roadmap that supports four things:
- the method actually solves the anchored problem
- the dominant contribution is real and focused
- the method is elegant enough that extra complexity is unnecessary
- any frontier-model-era component is genuinely useful, not decorative
Constants
- OUTPUT_DIR =
refine-logs/— Default destination for experiment planning artifacts. - MAX_PRIMARY_CLAIMS = 2 — Prefer one dominant claim plus one supporting claim.
- MAX_CORE_BLOCKS = 5 — Keep the must-run experimental story compact.
- MAX_BASELINE_FAMILIES = 3 — Prefer a few strong baselines over many weak ones.
- DEFAULT_SEEDS = 3 — Use 3 seeds when stochastic variance matters and budget allows.
Workflow
Phase 0: Load the Proposal Context
Read the most relevant existing files first if they exist:
refine-logs/FINAL_PROPOSAL.mdrefine-logs/REVIEW_SUMMARY.mdrefine-logs/REFINEMENT_REPORT.md
Extract:
- Problem Anchor
- Dominant contribution
- Optional supporting contribution
- Critical reviewer concerns
- Data / compute / timeline constraints
- Which frontier primitive is central, if any
If these files do not exist, derive the same information from the user's prompt.
Phase 1: Freeze the Paper Claims
Before proposing experiments, write down the claims that must be defended.
Use this structure:
- Primary claim: the main mechanism-level contribution
- Supporting claim: optional, only if it directly strengthens the main paper story
- Anti-claim to rule out: e.g. "the gain only comes from more parameters," "the gain only comes from a larger search space," or "the modern component is just decoration"
- Minimum convincing evidence: what would make each claim believable to a strong reviewer?
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.
- 7d ago First seen · 255 lines · 80 tokens per session scan A 9992828e9cdc
experiment-plan is a skill published in the GitHub repository zjunlp/Mechanist (71 stars, last pushed 11d ago), licensed MIT. It adds 80 tokens to every session and 2,485 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to experiment-plan, differing in 11 lines, and is treated as a copy.
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-ideation
Search academic literature and generate research hypotheses.
scienceworld-measurement-taker
Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a measurement tool. This skill covers acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting…
scienceworld-object-selector
Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category. This skill surveys visible objects with "look around", evaluates each against the task requirements…
scienceworld-threshold-evaluator
Use when the agent has just obtained a numerical measurement (temperature, weight, pH) and must compare it against a predefined threshold to determine a binary outcome. This skill extracts the measured value, evaluates it against the threshold condition (above/below), and executes the corresponding branch action such…