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/light0305/light-skills/light-experiment-codingnpx skills add Light0305/Light-skills --skill light-experiment-codinggit clone --depth 1 https://github.com/Light0305/Light-skillsWrote 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/light0305/light-skills/light-experiment-coding)<a href="https://agentmods.dev/skills/light0305/light-skills/light-experiment-coding"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-experiment-coding.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 | $0.00170 | $0.03305 |
| Opus 5 | $0.00085 | $0.01653 |
| Sonnet 5 | $0.00034 | $0.00661 |
| Haiku 4.5 | $0.00017 | $0.00331 |
Grade A, and why
light-experiment-coding 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
实验编码（stage 6）
任务不是“写出能跑的 notebook”，而是把上游冻结计划逐行实现成可证伪、可复跑、可审计的实验。优先级：
- 不改研究问题；
- 不让评估信息进入训练；
- 能用固定环境与 seed 真复跑；
- 保留足够 raw evidence，让 result-analysis 自己重算；
- 代码整洁和速度服从以上约束。
先完整阅读 references/experiment-coding-resource-map.md。工具机制见
references/tools.md，TDD/调试红旗见
references/tdd_redflags.md 与
references/debug_protocol.md。
入口：冻结输入
开始写码前读取并 hash：
- question / estimand；
- experiment matrix 每一行和 fair-comparison 常量；
- pre-registration 及 provenance；
- failure-tree report：每条 hypothesis 的 success/failure/inconclusive 分支、guardrail/counter-metric、kill criterion 与 amendment policy；
- data fixed revision、raw/curated SHA256、lineage、split ID、
split_leakageevidence； - result-analysis 对 raw run、predictions、metrics、failures、provenance 的消费契约；
- 当前 git commit 与 dirty state。
primary outcome、comparison family、exclusion、stopping 已冻结。若实现证明计划不可行，带最小复现和影响返回 research-plan，停下让人决策；不得改 config 默认值静默漂移。
实现顺序
1. 建立最小可运行项目
优先复制 assets/project-scaffold/：
uv.lock+pyproject.toml：uv sync --locked --extra dev；configs/experiment.schema.json：每个 matrix row 的机读配置；experiment_contracts.py：data/model/metric/preprocessing 最小接口；reproducibility.py：运行期 seed helper；- CI/pre-commit/debug 资产。
遵循现有仓库框架和配置格式；不要为一个实验引入付费 IDE、云追踪或私有 key。MLflow/DVC 可选，普通本地文件必须能完成
核心闭环。不可用资源明确写 UNAVAILABLE:原因，不假装通过。
2. 测试先行
在实现 preprocessing/train/eval 前：
- 写 gold test，验证人工可算的小答案；
- 写 property test（Hypothesis），验证范围、有限性、对称/单调等不变量；
- 写 metamorphic test，验证置换/等价变换后的输出关系；
- 写 train-only-fit 测试，记录 transformer 只收到训练折；
- 亲眼看新测试因缺实现或真实 bug 失败，再写最小实现使其通过。
浮点断言用 pytest.approx / assert_allclose(rtol, atol)。先声明 device、dtype、mixed precision 和容差；NaN/Inf
默认 fail。不要测“随机训练一定达到某个漂亮数”，测确定性边界和可重算事实。
3. 防泄漏实现
- holdout：先 split，再仅用 train
fit/fit_transform，test 只transform； - CV/调参：预处理器与模型放进 sklearn
Pipeline，每折只 fit training fold； - 患者/用户/牧场等实体用 group-aware split，不得跨 train/test；
- 目标编码、特征选择、PCA、imputation 同样只在训练折 fit；
- 数据件复核直接复用 data-engineering
split_leakage，不重造。
What ships with it
32 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.
- assets/project-scaffold/.github/workflows/ci.yml 1.0 KB
- assets/project-scaffold/.pre-commit-config.yaml 1.4 KB
- assets/project-scaffold/CODE_REVIEW_CHECKLIST.md 3.3 KB
- assets/project-scaffold/configs/experiment.example.json 765 B
- assets/project-scaffold/configs/experiment.schema.json 2.2 KB
- assets/project-scaffold/pyproject.toml 2.3 KB
- assets/project-scaffold/README.md 3.8 KB
- assets/project-scaffold/scripts/boundary_trace.py 2.9 KB runs code
- assets/project-scaffold/scripts/debug_instrument.sh 1.6 KB runs code
- assets/project-scaffold/src/example/__init__.py 87 B runs code
- assets/project-scaffold/src/example/experiment_contracts.py 2.7 KB runs code
- assets/project-scaffold/src/example/reproducibility.py 6.0 KB runs code
- assets/project-scaffold/src/example/stats.py 648 B runs code
- assets/project-scaffold/tests/conftest.py 632 B runs code
- assets/project-scaffold/tests/test_experiment_contracts.py 2.4 KB runs code
- assets/project-scaffold/tests/test_reproducibility.py 2.5 KB runs code
- assets/project-scaffold/tests/test_stats.py 532 B runs code
- assets/project-scaffold/uv.lock 157 KB
- examples/repro_spec.example.json 1.8 KB
- references/code_examples.md 3.1 KB
- references/debug_protocol.md 5.7 KB
- references/experiment-coding-resource-map.md 7.5 KB
- references/tdd_redflags.md 4.5 KB
- references/tools.md 3.4 KB
- scripts/experiment_execution_contract.py 56 KB runs code
- scripts/repro_gate.py 27 KB runs code
- scripts/review_gate.py 19 KB runs code
- scripts/run_artifact_check.py 25 KB runs code
- scripts/seed_audit.py 20 KB runs code
- templates/experiment-execution-contract.example.json 2.2 KB
- templates/run_manifest.md 2.7 KB
- templates/run_manifest.template.json 2.0 KB
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 · 208 lines · 170 tokens per session scan A 2cdad9b18f3c
light-experiment-coding is a skill published in the GitHub repository Light0305/Light-skills (587 stars, last pushed 2mo ago), licensed MIT. It adds 170 tokens to every session and 3,305 once invoked, about $0.0009 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
research-writing
科研论文写作助手，提供 30 个 Prompt 模板覆盖论文写作全流程。 当用户提到：论文写作、润色、翻译、文献综述、摘要、引言、方法章节、回复审稿人、 基金申请、研究计划、学术演讲 PPT、LaTeX 编辑、学术图表、实验结果分析、模拟审稿、 去 AI 味、文献对比、找研究空白、论文大纲时使用。 不要用于：非学术写作、创意写作、博客、商业文案、求职信、小说等场景。.
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
论文写作、修改、压缩和实验组织全流程中阻止【防御性写作】。把论文视为一场学术发布会， 而不是项目总结、实验日志或自我审查报告：识别这项工作最值得发表的价值，围绕它建立 最有利、最完整、最有说服力的叙事。不平均展示、不主动示弱、不写实验流水账、不替审稿人 攻击自己。 触发词：论文润色、论文修改、写摘要、写引言、写结论、压缩论文、rebuttal、回复审稿意见、 组织实验、论文AI味、防御性写作、心虚。.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper…
academic-citation
Search, verify, and map citations for CS/AI/ML papers. Produces VERIFIED/UNVERIFIED reference lists with Citation-to-Claim maps and Exemplar Sets. Use when: finding references for a paper section, verifying citation accuracy, building exemplar sets for introduction/related work learning, checking if existing citations…