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 zgbrenner/agentcounsel --skill antitrust-risk-intakegit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/zgbrenner/agentcounsel/antitrust-risk-intake)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/antitrust-risk-intake"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/antitrust-risk-intake/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/zgbrenner/agentcounsel/antitrust-risk-intake"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/antitrust-risk-intake.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 | $0.00087 | $0.02428 |
| Opus 5 | $0.00044 | $0.01214 |
| Sonnet 5 | $0.00017 | $0.00486 |
| Haiku 4.5 | $0.00009 | $0.00243 |
Grade A, and why
Antitrust Risk Intake 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Antitrust Risk Intake
Purpose
Take unstructured facts about conduct with possible competition-law exposure — a worried email, a proposed arrangement, a hotline report, an agency letter — and organize them into a conduct inventory and triage matrix that buckets each item, records preliminary risk indicators from the shared catalog, flags any time-critical track, and routes each item to the matched antitrust deep-dive skill. This is the front door of the antitrust-competition cluster, and its output is a draft for attorney review: every bucket and routing call is a workflow signal, never a legal classification or an assessment of legality.
Use When
- A business team forwards an email thread about a competitor contact, meeting, or "understanding" and asks legal whether it is a problem.
- Several loosely described conduct items arrive at once — a JV idea, a pricing move, a distributor complaint — and counsel needs them inventoried, bucketed, and routed before any deep-dive work.
- A hotline report, internal-audit finding, or news of an industry investigation raises possible exposure and the facts need structured intake.
- An agency letter, dawn-raid rumor, or pending merger notification makes it urgent to identify which track is time-critical.
- Counsel asks "which antitrust skill do I run on this?" and the answer needs a documented triage matrix with fact gaps listed per recommended deep-dive.
Required Inputs
- Jurisdiction(s) of competitive effect — every country and, where relevant, state/province where the conduct has effects, or
[verify jurisdiction]. The analysis follows the markets, not the parties' headquarters. - Business sector and footprint — industry, products/services, geographic reach, sales channels. Mark unknowns
unknown/not found/not provided/ambiguous. - Conduct description — what is, was, or will be done. Each conduct item gets its own row, with: who, what, when, where, and (if multi-party) which counterparties.
- Counterparty competitive posture — for each counterparty, the user's view of whether they are a direct competitor, potential competitor, customer, supplier, distributor, or unrelated. Multi-role flags allowed.
- Candidate conduct buckets the user suspects in scope — horizontal collaboration, vertical restraint, information exchange, pricing-related conduct (RPM / MAP / MFN / loyalty), merger or acquisition, monopolization / abuse of dominance / unilateral conduct, trade association or standard-setting, gun-jumping or integration planning, distribution or channel conduct, algorithmic pricing, labor-market conduct (no-poach / wage-fixing), or other. The bucket is a starting point, never a conclusion.
- Urgency posture — planned future conduct (pre-clearance triage), ongoing conduct (compliance triage), past conduct subject to investigation or litigation (defensive triage), or no investigation. User-supplied dates only, all marked
[deadline verification required]. - Documents and source anchors — what the user has supplied and the section/page/clause for each extracted fact.
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 · 114 lines · 87 tokens per session scan A 0d47fddb77ce
Antitrust Risk Intake is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 2,428 once invoked, about $0.0004 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
cross-check-legal-advice
How to safely use AI for legal issue-spotting, contract clause translation, and preparing targeted questions for licensed legal counsel.
mk:intake
Ticket/PRD intake: product area classification, completeness scoring, RCA, technical assessment. Works with Jira (via mk:jira-issue / jira-as), Linear (via MCP), GitHub (via gh CLI), or manual paste. Triggers: 'analyze ticket', 'intake PRD', 'triage issue', 'classify ticket', 'check ticket'.
legal-research
A legal research skill for finding and analysing laws and court cases, including similar cases. It requires access to a reliable legal research database before producing a formal report.
document-fill
A document-filling assistant that uses a supplied template and case files to fill in forms, contracts, or legal documents. It also reports where each filled value came from and which details are missing.
contract-review
A contract-review workflow for agreements governed by Chinese law, United States law, or both. It examines clauses one by one and produces a list of legal-risk questions, with an optional marked-up Word document.
fedramp
Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…