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-upstreamgit 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-upstream)<a href="https://agentmods.dev/skills/li-ch/law-skills/law-upstream"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-upstream/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-upstream"><img src="https://agentmods.dev/badge/skills/li-ch/law-skills/law-upstream.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 | $0.00053 | $0.00619 |
| Opus 5 | $0.00026 | $0.00309 |
| Sonnet 5 | $0.00011 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
law-upstream 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.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAW Upstream
Merge local paper modifications back to ~/.common-law/. This keeps the global bib file, writing guide, and build scripts in sync across all papers.
What gets tracked
Three categories of local changes:
- New bib entries — citations added to the paper's
refs.bibthat don't exist in~/.common-law/bib/refs.bib - CLAUDE.md changes — modifications to the writing guide (excluding the "Paper Narrative" section)
- Script changes — modifications to
build.sh,build.bat, orverify.sh
Workflow
Step 1: Scan for changes
Run scripts/upstream-bib.sh to find new bib entries and scripts/upstream-claude.sh to find CLAUDE.md changes.
For script changes, diff the paper's scripts against the skill's canonical copies.
Step 2: Present options to user
Show a grouped list:
Changes ready to upstream:
[Bib entries — 3 new]
1. extraref1 — "Machine Learning for Resource Management..." (Garcia, EuroSys 2025)
2. extraref2 — "Reinforcement Learning for Cluster Scheduling" (Nguyen, MLSys 2024)
3. extraref3 — "A Formal Analysis of Joint..." (Tanaka, PER 2025)
[CLAUDE.md changes]
4. Added "No hyphens" rule to Hard Prohibitions section
[Script changes]
(none)
Select items to upstream (e.g., "1,2,4" or "all"):
Step 3: Merge selected changes
- Bib entries: append to
~/.common-law/bib/refs.bib, deduplicate by citation key - CLAUDE.md: strip the "Paper Narrative" section and everything below it, then merge changes into
~/.common-law/paper-style/CLAUDE.md - Scripts: copy to the corresponding skill's
scripts/directory
Step 4: Report
Tell the user exactly what was merged and where.
Prompted by other skills
After law-write or law-revise sessions that add citations, ask: "You added N new citations. Upstream them to the global bib?"
The user can say yes, no, or "later." Do not push.
Scripts
scripts/upstream-bib.sh— finds new bib entries and handles deduplicationscripts/upstream-claude.sh— diffs CLAUDE.md and strips the narrative section
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.
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 · 67 lines · 53 tokens per session scan A c913c0465de4
law-upstream is a skill published in the GitHub repository li-ch/law-skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 619 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…