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-revisegit 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-revise)<a href="https://agentmods.dev/skills/li-ch/law-skills/law-revise"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-revise/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-revise"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-revise.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 | $0.00058 | $0.00618 |
| Opus 5 | $0.00029 | $0.00309 |
| Sonnet 5 | $0.00012 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
law-revise 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAW Revise
Implement revision items from the paper's todo.md, rebuilding and committing after each change.
Workflow
Step 1: Read todo.md
Read the paper's todo.md to understand which items to implement and their priority.
If the item is marked ⏳ WAITING ON DATA or requires experiments (code execution, data collection, hardware access), do not attempt to implement it. Tell the user: "This item requires experiments the agent cannot run. Use law-call4expr to create an experiment guide if one doesn't already exist."
Step 2: Implement one item at a time
For each item the user asks to implement:
- Read the relevant
.texfile(s) fromsections/ - Make the change described in the todo.md item
- Run
law-buildto rebuild the paper - If build succeeds: commit with message
[R{n}] {item-code}: {description} - If build fails: stop immediately and report the error to the user. Do NOT continue to the next item.
Step 3: Cross-section items
If an item affects multiple sections (e.g., "R1-3: Fix convergence proof (§4.2, §7.2)"), edit ALL affected files before rebuilding and committing. Do not commit partial changes.
Step 4: After all items
Produce a summary:
- Items completed
- Items deferred (not asked to implement)
- Any build failures encountered
- Remind user to run
law-verifyif it wasn't already run bylaw-build
Commit message format
[R{n}] {item-code}: {short description}
Example:
[R1] R1-1: add coherence model subsection to §4.3
Agent decides commit granularity. If a change is simple (one paragraph), one commit. If a change touches multiple files and is conceptually one item, also one commit. If the changes are logically separate, separate commits.
Safety rules
- Never implement items the user did not explicitly ask for
- Never create new citations — use
~\cite{}with empty braces if a citation is needed - Never modify section labels (
\label{}) unless the item explicitly requires it - Never change the document class or style files
- If an item says "add a figure" but the figure doesn't exist, use
figs/placeholder.pngand add\textcolor{red}{TODO: add figure}to the text - After build failure: show the user the error from
temp/main.log, do not guess at fixes
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.
- 12d ago First seen · 61 lines · 58 tokens per session scan A 8f7df441bd44
law-revise is a skill published in the GitHub repository li-ch/law-skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 618 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…