Use when a user needs a direct, low-friction response for research, studying, writing, planning, decisions, administrative work, troubleshooting, or a multi-turn project, especially when they seem overwhelmed, distracted, stuck starting, interrupted, burdened by too many options, or likely to lose the active thread.
Instructions for zgbrenner/agentcounsel, covering agents.md — agentcounsel, what this repository is, first, decide which job you are doing, job 1 — using a skill and non-negotiable rules.
Instructions for zgbrenner/agentcounsel, covering claude.md — agentcounsel, before anything else, routing efficiently, editing the library with claude code and a pre-handoff self-check.
Instructions for zgbrenner/agentcounsel, covering agentcounsel — gemini cli context, non-negotiable operating model and how to work in this repository.
Use when a new or modified AI/ML use case needs to be documented and triaged so legal, compliance, and governance teams can assess risk and route it to the right specialists.
Use when reviewing a general commercial contract — such as a master services agreement, vendor agreement, supplier contract, or professional services agreement — to produce a structured risk assessment and prioritized issue list for attorney review.
Use when drafting a demand letter for attorney review — running a structured intake, a pre-draft risk gate, and a draft with every legal conclusion, damages figure, and deadline flagged for attorney confirmation before sending.
Use when reviewing a data processing agreement (DPA) or data processing addendum to produce a structured risk summary and prioritized issues for attorney review.
Use when producing a structured legal research memo in response to a specific legal question, organizing analysis using IRAC discipline (Question Presented, Brief Answer, Facts, Assumptions, Discussion/Analysis, Conclusion) with explicit sourcing requirements and attorney verification checkpoints.
Use when building a factual timeline for litigation from provided source documents, producing a structured chronology table with citations, disputed/undisputed flags, and gap analysis for attorney review.
Use when reviewing a non-disclosure or confidentiality agreement to produce a triage rating (route, flag, or stop), a structured risk summary, and prioritized redline points for attorney review.
Use when organizing and reviewing the facts surrounding a proposed employee termination so an attorney can assess legal risk before the termination occurs.
Use when reviewing the terms of service, API agreement, or usage policies of an AI vendor or AI-enabled service to produce a structured risk summary and prioritized redline points for attorney review.
Use when reviewing a draft internal employee AI-use policy — or drafting review criteria when no policy exists — to identify gaps, inconsistencies, and priority issues for attorney and HR review.
Use when triaging the legal and governance risk of a specific AI model or AI system before or during deployment, to produce a structured risk register and recommended controls for attorney and governance review.
Use when a company's antitrust compliance policy, competition code-of-conduct section, or training program needs a gap review — after an incident, an acquisition, a regulatory development, or as a periodic refresh — to produce a draft topic-coverage and jurisdiction-coverage matrix, training/reporting and dawn-raid…
Use when facts with possible competition-law exposure first arrive — a sales email about a competitor contact, a proposed collaboration, a pricing move, a hotline report, or an agency inquiry — to produce a draft conduct inventory and triage matrix that buckets each item, flags any time-critical track, and routes each…
Use when a proposed JV, co-development, co-marketing, joint purchasing, joint bidding, benchmarking, or standard-setting arrangement between actual or potential competitors needs antitrust screening, to produce a draft hardcore-restraint flag list, information-flow matrix, ancillarity questions, and per-jurisdiction…
Use when a distribution, dealer, franchise, or marketplace program contains resale-price (RPM/MAP), territory or customer, online-sales, marketplace-ban, dual-pricing, exclusivity, or selective-distribution restraints, to produce a draft restraint inventory with per-jurisdiction character flags, ancillarity notes, and…
Use when an agreement contains exclusivity, requirements, MFN/parity, loyalty-discount, rebate, or bundling provisions — a supply deal with a share-based rebate cliff, a platform demanding price parity — to produce a draft restraint classification, foreclosure-relevant facts table, MFN/parity matrix, and…
Use when merger parties between signing and closing are planning integration, sharing information, or proposing joint conduct — aligning pricing, joint customer calls, a co-branded announcement before the waiting period ends — to produce a draft covenant inventory, conduct-vs-covenant deviation log…
Use when actual or potential competitors propose to exchange competitively sensitive data — M&A diligence requests, JV data flows, benchmarking submissions, a negotiation asking for cost or capacity data — to produce a draft information-item matrix with per-item sensitivity flags, clean-team design notes, and…
Use when a contemplated or signed acquisition, merger, JV, or minority investment needs first-pass antitrust issue-spotting — an LOI with a competitor, diligence underway, the board asking where filings may be needed — to produce draft horizontal-overlap and vertical-relationship matrices, filing-question and…