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 ThomasMoreAI/legal-skills-open --skill pi-brief-formatgit clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/pi-brief-format)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/pi-brief-format"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/pi-brief-format/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/thomasmoreai/legal-skills-open/pi-brief-format"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/pi-brief-format.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 | $0.00073 | $0.01220 |
| Opus 5.5 | $0.00029 | $0.00488 |
| Sonnet 5.5 | $0.00015 | $0.00244 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
pi-brief-format 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 24d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-brief-format
Specter's response template for "lawyer asked about a statute." This skill turns a raw Harvester record into a structured brief — not a Wikipedia summary.
When to use this skill
Use it any time harvester_query.lookup_citation() or harvester_query.search() returns a hit and the user is asking about that statute. Examples:
- "What's CVC 23152(a)?" → lookup, then brief format
- "DUI laws in California?" → search top hit, then brief format on the top result; offer to brief others
- "Pull me the negligence-per-se argument for Cal. Veh. Code § 22350" → lookup, brief format, point at the NPS section
Don't use it when the user is asking a non-statute question (case strategy, procedural questions, conversational). The brief format is overkill for those — just answer in voice.
How to call
The renderer lives in api/pi_brief.py at the repo root. Two paths to invoke:
Shell (use this from exec inside an OpenClaw turn)
cd ~/Specter && .venv/bin/python -m api.pi_brief lookup "Cal. Veh. Code § 23152(a)"
That runs the full pipeline: hits the local Specter API at $SPECTER_API (default http://127.0.0.1:8000), looks up the citation, renders the brief with ANSI colors stripped (since stdout isn't a TTY when Specter calls exec).
Python (use this from a sub-skill or programmatic flow)
import sys, pathlib
sys.path.insert(0, str(pathlib.Path("~/Specter").expanduser()))
from api.pi_brief import build_brief, render_text
# `record` is whatever harvester_query.lookup_citation returned.
brief = build_brief(record)
whatsapp_text = render_text(brief)
render_text is the WhatsApp-friendly renderer (no ANSI, plain emoji, ~3-4 message-block sized output). render_ansi is for the terminal.
Output shape
The brief block has these sections, in order:
- 🥃 Citation header — citation + statute title.
- Bluebook — formatted for a brief or letter, e.g.
Cal. Veh. Code § 22350 (West 2024). - Pull quote (paste-ready) — the statute language, de-bracketed, ready for a complaint or motion.
- PI angle — per factor — for each contributing factor on the statute:
- NPS availability marker (
✅ available,⚠️ qualified,❌ rare) - Class of victim
- Class of harm
- One-line "why this matters in PI"
- Common defenses
- Evidence to gather
- NPS availability marker (
- Context (non-canonical PI tags) — present only when a record has
pi_context_tags(e.g., "Bicycle Violation", "Equipment"). Marked as non-canonical so the lawyer can tell context from canonical-eval-tag. - Source — the verifiable URL.
- Specter notes — flagged commentary block. Auto-derived from playbook content (NPS availability summary, punitive flag, collateral-estoppel flag). Never LLM-generated.
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.
- 24d ago First seen · 91 lines · 73 tokens per session scan A 2d583f70d153
pi-brief-format is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,220 once invoked, about $0.0003 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 2026-10-04.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…