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 harvester-querygit 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/harvester-query)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/harvester-query"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/harvester-query/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/harvester-query"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/harvester-query.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 | $0.00057 | $0.01506 |
| Opus 5.5 | $0.00023 | $0.00602 |
| Sonnet 5.5 | $0.00011 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
harvester-query 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harvester-query
Specter's Harvester is a FastAPI service that fronts two Chroma collections:
| Collection | Contents | When the API uses it |
|---|---|---|
specter_statutes |
384 US motor-vehicle statutes (CA, TX, FL, PA, IL, OH) | default — any US-jurisdiction or generic query |
canada_pi_cases |
340 real Canadian PI cases (CanLII, with damages, injury type, plaintiff_won, deciding_factor) | auto-routed when the query mentions Canada / Ontario / Quebec / Toronto / ONSC / ONCA / canlii / etc., or when ?jurisdiction=Canada or ?state=CA-CAN is passed |
Every citation the user sees should come from the Harvester (or, on miss, from a verified web source). Never fabricate.
When to use this skill
- Always for fact patterns mentioning Canada or a Canadian province / city. The Canada collection is indexed on facts of decided cases, so messy fact patterns ("child got hurt outside Target in Ontario", "slip and fall on icy sidewalk in Toronto") are EXACTLY what it's good at. Run
searchfirst; ask follow-ups only after showing what hit. - User asks for a specific citation: "what's Cal. Veh. Code § 23152(a)?" →
lookup_citation - User asks a semantic / topical question: "DUI statutes in California", "laws about texting while driving" →
search - User asks an open question and you want top-k candidates: "any state with a hit-and-run analog to CVC 20001?" →
ask - User uses a synonym ("speeding", "drunk driving", "texting") — map it to one of the 17 canonical contributing-factor categories before passing as a
factorfilter (see categories below).
When NOT to use it
- Pure procedural / case-strategy questions ("how do I file?") — the Harvester only holds statutes (US) and case law (Canada).
- Greetings, identity questions, persona check-ins — answer in voice without calling the API.
- Questions that don't require a citation (Specter can answer general PI-law-shape questions briefly without one, but must not invent a citation to back them up).
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.
- 1mo ago First seen · 131 lines · 57 tokens per session scan A 497236e211c1
harvester-query is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,506 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 2026-09-03.
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…