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-reviewgit 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-review)<a href="https://agentmods.dev/skills/li-ch/law-skills/law-review"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-review/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-review"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-review.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 | $0.00050 | $0.00811 |
| Opus 5.5 | $0.00020 | $0.00324 |
| Sonnet 5.5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
law-review 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 2mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAW Review
Parse reviewer feedback into a structured todo.md using the standard format defined in ~/.common-law/paper-style/todo-format.md.
Workflow
Step 1: Read the reviews
Read all review files from the paper's reviews/ directory. Reviews are plain text or markdown files containing reviewer comments, scores, and recommendations.
Step 2: Extract actionable items
For each review, identify every concrete action the reviewer is asking for. Skip vague praise, skip generic complaints without specific asks. An item is "actionable" if you can answer "what file do I edit and what do I change?"
Step 3: Assign priority
| Level | Criteria |
|---|---|
| P0 | Reviewer explicitly states this is required for acceptance. The paper will be rejected without it. |
| P1 | Major concern that strongly impacts the reviewer's score. Addressing it significantly strengthens the paper. |
| P2 | Minor issues: typos, grammar, formatting, figure readability, missing citations, clarifications. |
If unsure about priority, flag it and default to P1.
Step 4: Group by review round
Use the round prefix R1, R2, R3, etc. If this is the first review, use R1. If reviews span multiple rounds (revision and re-review), create separate sections per round.
Step 5: Write todo.md
Write the output to todo.md. Reference ~/.common-law/paper-style/todo-format.md for the exact format.
Item code format:
R{n}-{number}— sequential within round- Cross-section items: append affected sections as
(§X.Y, §Z) - Uncertain items: prefix with
⚠️ UNCERTAIN:
Example:
- [ ] R1-1. Add coherence model subsection to §4.3 (0.3 day)
- [ ] ⚠️ UNCERTAIN: R1-5. The reviewer mentions "failure modes" — is this a new subsection or a paragraph?
Step 6: Report to user
After writing todo.md, tell the user:
- How many items were extracted (by priority)
- Which items are flagged as UNCERTAIN
- "Please review and adjust priorities before I implement anything."
What ships with it
1 file 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.
- 2mo ago First seen · 72 lines · 50 tokens per session scan A d4bf62e6d636
law-review is a skill published in the GitHub repository li-ch/law-skills (11 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 811 once invoked, about $0.0002 per session on Opus 5.5. 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.
law-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| law-reviewli-ch/law-skills | Skill | 11 | 9d ago | MIT | A | 50 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |