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-writegit 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-write)<a href="https://agentmods.dev/skills/li-ch/law-skills/law-write"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-write/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-write"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-write.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 | $0.00064 | $0.01769 |
| Opus 5.5 | $0.00026 | $0.00708 |
| Sonnet 5.5 | $0.00013 | $0.00354 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade C, and why
law-write scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sL "https://www.skillhub.club/api/v1/skills/blader-humanizer/install?agents=opencode&format=sh" | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL "https://www.skillhub.club/api/v1/skills/blader-humanizer/install?agents=opencode&format=sh" | bash How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAW Write
Write or edit LaTeX paper sections following Li's Academic Writing conventions. Every output must conform to the 26 writing rules defined in references/writing-rules.md.
For the owner' + chr(39) + 's inline % comments in tex sources, run the law-issues cycle (capture verbatim into the paper' + chr(39) + 's ISSUES.md, fix, describe, generalize, verify, commit); do not process them inline here.
Before writing
Read these files to understand the paper's context:
CLAUDE.md— the paper's narrative (challenges, design decisions, key results) at the bottomAGENTS.md— paper macros (\sys), venue, page limit, section structuremain.texpreamble — document class, loaded packages, defined macros- Existing sections in
sections/— labels already used, cross-references to maintain
If CLAUDE.md has an unfilled "Paper Narrative" section, warn the user: "The paper narrative in CLAUDE.md is not filled in. I can write without it, but the content may not align with the paper's story. Fill it in for best results."
Writing rules (summary)
Core rules (see references/writing-rules.md for full details with examples):
- Active voice, present tense, first person ("We find that..."); our own work takes we/our/ours as the sentence subject wherever grammatical (rule 25), and attack-enabling conditions get negative verbs, never "cheap" framing
- Lead every paragraph with its main claim
- Quantify every claim with specific numbers in normal weight
- Name your discoveries with
\emph{} - Never hedge — "This exposes a gap" not "This may suggest a gap"
- Ground mechanisms in expert behavior: "Operators do X. Our system does Y."
- One idea per sentence; no stacked subordinate clauses
- No long dashes (
---or--); hyphens in compound words are fine; never begin a sentence with a number (rule 24), and no number or A/An opens any title, paragraph, or sentence (rule 26) - No
\textbf{}mid-paragraph (bold numbers are OK);\noindent\textbf{Label.}for run-in heads - Code names in
\texttt{}, system name as\sys \resizeboxfor all tables;algorithm/algpseudocodeonly for algorithms- Leave
\textcolor{red}{##?}for missing numbers,\textcolor{red}{TODO:}for unfinished work - Macro entities act through the authors: "We build a prototype that..." never "A prototype ...s" — only functions/processes/classes/contracts may be active subjects of their own mechanics
- Never use "X, not Y" contrastive apposition (nor "not X but Y" / rhetorical "rather than") — state the positive claim; give the contrast its own sentence
- Sentence-level coherence: every pair of adjacent sentences must connect — transition, elaboration, contrast, or consequence. Never change subject abruptly between neighboring sentences; rebuild the paragraph's spine so one idea develops in sequence
- No one-sentence paragraphs, ever — expand with reasoning, merge with a neighbor, or cut entirely
- Scope extraordinary claims: sweeping universals ("nothing reproduces", "no tool survives X") require inline evidence or an explicit scope ("in the systems we examined"); rule 5 forbids weak hedging verbs, never evidence-scoping of strong claims
What ships with it
3 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.
- 9d ago Changed · +3 lines 6a64666d3d6e
- 11d ago Changed · +6 lines 50a523a64ff7
- 2mo ago First seen · 116 lines · 64 tokens per session scan C 5fc1da52d62e
law-write is a skill published in the GitHub repository li-ch/law-skills (11 stars, last pushed 9d ago), licensed MIT. It adds 64 tokens to every session and 1,769 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
law-write compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| law-writeli-ch/law-skills | Skill | 11 | 9d ago | MIT | C | 64 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |