A workflow for handling inline comments in LaTeX papers, where LaTeX is a text-based system for writing documents such as research papers. It records each comment, fixes the source files, explains the fixes, and verifies the build.

Use it when an owner leaves percent-sign comments in .tex files to capture issues, apply corrections, promote recurring lessons to rules, and commit a verified result.

It prevents reviewer or owner comments from being lost and provides a repeatable record of what was changed.

law-issues — Skill for Claude Code and Codex by li-ch/law-skills

Install

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.

Any agent

npx skills add li-ch/law-skills --skill law-issues

Clone the repo

git clone --depth 1 https://github.com/li-ch/law-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/li-ch/law-skills/law-issues/github.svg)](https://agentmods.dev/skills/li-ch/law-skills/law-issues)

Your own site

<a href="https://agentmods.dev/skills/li-ch/law-skills/law-issues"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-issues/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/li-ch/law-skills/law-issues"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-issues.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01216
Opus 5.5	$0.00000	$0.00486
Sonnet 5.5	$0.00000	$0.00243
Haiku 4.5	$0.00000	$0.00122

Measured 11d ago against content hash 5a6d073a7348, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

law-issues 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/capture_comments.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

law-issues/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: law-issues

LAW Issues

Standardize the inline comment/fix cycle for LaTeX papers: the owner edits .tex files and leaves % comments; you capture every comment verbatim into a persistent ISSUES.md ledger, fix each one in the sources, describe each fix in plain language, promote recurring lessons into standing rules, and land the round with a verified build and a commit.

When to use

The owner says anything like "I updated the tex, look at the comments", "I am disappointed, fix them", or a .tex file shows new inline % comments after an owner edit.
NOT for external reviewer reports on a submission (use law-review for those; it builds a todo.md revision tracker) and NOT for implementing such a tracker (that is law-revise). This skill is the tight author-side loop over inline % comments.

Procedure (fixed order; do not reorder)

Step 1 — CAPTURE (before any fix)

Find the edited files (git status, newest mtimes in sections/). Run the capture helper for a numbered verbatim list:

python3 <skill-dir>/scripts/capture_comments.py <paper-root>

Append a new round section to ISSUES.md in the paper root BEFORE touching any source. Numbers continue monotonically across rounds (never renumber; a 30-item ledger is the point). Quote comments VERBATIM, exactly as written, including profanity and typos: the ledger is the record of what the owner actually said. Remove each comment from the .tex only after it is captured here.

Exact ISSUES.md entry format:

---

# Round N (YYYY-MM-DD)

**<n>. <short descriptive title>**

> <verbatim comment, wrapped exactly as written>

**Fix.** <plain, simple, direct sentences: what was wrong, what was
done, where in the paper it landed. Written AFTER the fix, in past
tense. Note standing-rule promotions here. For items that cannot be
fixed by writing, state that plainly and name the real work item.>

Step 2 — FIX

Apply fixes in the sources under the current law-write rules (25 of them at time of writing; rules 24 and 25 themselves came out of this cycle) and the paper repo's AGENTS.md and CLAUDE.md conventions. Sweep the whole paper when a comment names a pattern rather than a spot (tone, voice, banned constructions) — a local fix for a global rule fails the round.

Read the full file on GitHub · 130 lines

Files

What ships with it

2 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.

Changes

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.

11d ago First seen · 130 lines · 0 tokens per session scan A 5a6d073a7348

Subscribe to this mod's changes

law-issues is a skill published in the GitHub repository li-ch/law-skills (11 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,216 tokens. 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 2026-10-27.

Scientific Writing and docs

law-issues next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
law-issuesli-ch/law-skills	Skill	11	9d ago	MIT	A	0	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