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/evoclaw/amplify/experiment-executionnpx skills add EvoClaw/amplify --skill experiment-executiongit clone --depth 1 https://github.com/EvoClaw/amplifyWhat 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 | $0.00048 | $0.08413 |
| Opus 5 | $0.00024 | $0.04207 |
| Sonnet 5 | $0.00010 | $0.01683 |
| Haiku 4.5 | $0.00005 | $0.00841 |
Grade A, and why
experiment-execution 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 3d 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 — 794 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Execution (Phase 4)
Overview
This skill orchestrates all implementation and experimentation. It operates in TWO stages:
- Phase 4a (Exploratory): Quick, focused exploration to validate assumptions and discover insights BEFORE committing to full-scale execution. This stage may reveal that the research question or method design needs refinement.
- Phase 4b (Full Execution): Complete, rigorous execution of the (possibly refined) plan.
This two-stage model reflects how real research works: you don't know everything before you start, and early exploration often reshapes the direction.
On-Demand Literature Search (Active Throughout Phase 4)
Literature retrieval is NOT limited to Phase 1. During experiment execution, when you encounter unexpected results, need to understand a technique, or want to compare with a method not in the original literature review — search immediately. Use web search, arXiv, Google Scholar. Add new papers to docs/02_literature/paper-list.md with tag [Found during Phase 4].
If search fails or returns insufficient results:
- Try alternative search terms (synonyms, broader/narrower scope, different field terminology)
- If still insufficient → note what was searched and what's missing in
docs/02_literature/paper-list.md - Ask the user: "I need papers on [topic] but couldn't find them via [methods tried]. Can you point me to relevant work?"
- Do NOT block on literature — proceed with available information and mark the gap as
[literature pending]
Global Constraints
Inject ALL of these into every subagent dispatch during Phase 4:
- VALUE_ANCHOR: "This project's value proposition is: [read
value_propositionfromdocs/01_intake/research-anchor.yaml]. All work serves this." - METRIC_LOCK: "Primary metrics are [read
primary_metricsfromdocs/03_plan/evaluation-protocol.yaml]. IMMUTABLE without user permission." - VENUE_ALIGNMENT: "Target venue: [read
target_venue.primaryfromresearch-anchor.yaml]. Is current experiment scale adequate?" - ANTI_CHERRY_PICK: "All seeds. All results. All failures recorded."
- PREMATURE_EXPERIMENT_GUARD: "Baselines must be reproduced before running own method at full scale."
What ships with it
4 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.
- 3d ago First seen · 794 lines · 48 tokens per session scan A 4b1666618e4b
experiment-execution is a skill published in the GitHub repository EvoClaw/amplify (12 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 8,413 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
paper2poster
Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…
paper2slides
Turn an academic paper PDF into a presentation deck (.pptx) end-to-end. Use this skill whenever the user wants to "make slides from a paper", "generate a deck from this PDF", "make a PPT from this paper", "generate slides from a PDF document", "make a deck from a research paper", or supplies a research paper PDF and…
5writing
数学建模竞赛论文撰写阶段，支持 Typst 和 LaTeX 双引擎。根据 ANALYSISMODELINGREPORT.md、RESULTSREPORT.md 和 figures/.pdf 选择比赛模板、排版引擎、组织章节，并在论文正文中按章节直接插入图表。.
6verity
数学建模竞赛最终验证和验收阶段，支持 Typst 和 LaTeX 双引擎。用于论文写完后检查章节数量、标题顺序、图表引用、数值一致性、占位符、内部文件泄露、参考文献、代码可复现性、编译和提交就绪状态。.
1start-mathmodel
数学建模竞赛工作流入口。用于启动完整建模流程：询问用户偏好，生成 plan.md 和 todo.md，并按阶段调用赛题分析、建模、代码与图表、流程图、论文撰写、验证验收等 skills。.
4drawio
数学建模非数据型图示绘制阶段。根据 ANALYSISMODELINGREPORT.md、RESULTSREPORT.md 和已有 figures/ 生成技术路线图、子问题求解流程图、模型结构图、数据处理流程图等 DrawIO 图，并导出论文可引用 PDF。.