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 li-ch/law-skills --skill law-call4exprgit clone --depth 1 https://github.com/li-ch/law-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/li-ch/law-skills/law-call4expr)<a href="https://agentmods.dev/skills/li-ch/law-skills/law-call4expr"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-call4expr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/li-ch/law-skills/law-call4expr"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-call4expr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.00790 |
| Opus 5 | $0.00039 | $0.00395 |
| Sonnet 5 | $0.00016 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
law-call4expr 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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAW Call for Experiments
Write experiment guides for human execution. These guides hand off work that the agent cannot complete: running code, collecting data, producing figures, or accessing hardware.
When to use this skill
Use when todo.md contains items that the agent cannot complete. These items are marked ⏳ WAITING ON DATA in todo.md with a pointer to the experiment guide. The guide is a task list, not a narrative — the person executing it should not need to read reviews or understand the paper's narrative.
Writing rules
Rule 1: No justification
The person running experiments knows why. Tell them what to produce, not why. Remove all "because the reviewer said" or "this validates assumption X" language.
Rule 2: Three deliverables per experiment
Every experiment must specify exactly three outputs:
- CSV file — path in
data/, column names, what each column contains - Plotting script — path in
figs/, what CSV it reads, what plot it produces - Final figure — path in
figs/, the PNG file name
Never say "report the results" or "add a figure." Always specify exact file paths.
Rule 3: Never reference reviewers
The guide is a task list. No reviewer names, no paper state, no priority justifications based on reviewer impact. If prioritization is needed, use a simple numbered list.
Rule 4: Language matches audience
Write in the language the executor prefers. Default to Chinese — the guide targets a Chinese-speaking PhD student. If the user explicitly asks for English, or if the agent cannot determine the audience's language, write in English.
Do not assume Chinese is always correct. If the user says "my student speaks English," write in English.
Templates
Use the template that matches the language. Default to Chinese unless the user specifies otherwise.
Chinese template
# [Paper Name] 补充实验
## 实验 N: [Name]
### 数据收集
- [Step 1]
- [Step 2]
### 交付物
- **CSV:** `data/xxx.csv`
- 列：`col1, col2, col3`
- **绘图脚本:** `figs/fig-xxx.py`
- 读取 `data/xxx.csv`
- 输出：[description of plot]
- **最终图:** `figs/fig-xxx.png`
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.
- 9d ago First seen · 90 lines · 0 tokens per session scan A b0d939ec53a0
law-call4expr is a skill published in the GitHub repository li-ch/law-skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 790 once invoked, about $0.0004 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…