AgentCounsel
An open, Markdown-native library of legal skills for AI agents — and the legal professionals who supervise them.
AgentCounsel is a collection of standalone legal skills. Each skill is a structured workflow that helps an AI agent — or a lawyer — produce draft legal work product for attorney review. The skills supply discipline and structure: how to scope a task, what inputs to gather, how to organize the output, and what a supervising attorney must verify before anything is relied upon.
AgentCounsel does not provide legal advice. It produces draft work product intended for review and adoption by a qualified, licensed legal professional. Using it does not create an attorney–client relationship.
New here? Start with QUICKSTART.md — it walks through your first skill run in about five minutes.
Who AgentCounsel is for
- Practicing lawyers and in-house legal teams who want AI assistance that is consistent, reviewable, and built around attorney oversight instead of around a vendor's product.
- Legal operations and knowledge-management teams standardizing how their organization uses AI for routine legal work — intake, triage, first-pass review, and drafting.
- Law students and new lawyers who want to see how experienced practitioners structure a contract review, a chronology, a research memo, or a risk assessment.
- AI builders and engineers assembling legal agents or assistants who need well-scoped, safety-first workflow definitions they can drop into any model or framework.
Whoever you are, the assumption is the same: a licensed attorney reviews the output before it is used.
What it is — and is not
It is:
- A library of legal workflows and output structures.
- A way to make AI-assisted legal drafting more consistent, reviewable, and safe.
- Useful piecemeal (one Markdown file) or as a whole.
- Plain Markdown at its core, with no required runtime, account, or vendor lock-in. An optional MCP catalog provides typed routing and selective context retrieval.
It is not:
- Legal advice, or a substitute for a licensed attorney.
- A source of jurisdiction-specific legal rules. Skills give you process and structure, not the law of any jurisdiction.
- A finished-document generator. Every output is a draft that an attorney must review.
- Built around any single AI product. It is a portable library with thin adapters for many environments.
Quick start
QUICKSTART.md is the one place to start — pick your platform, install a practice-area pack, and run your first skill in about five minutes. Sample outputs are in examples/.
You do not need to read core/ to get started: every pack and adapter loads those operating rules for the AI automatically. Read core/ yourself only if you are using a raw SKILL.md file on its own, or you want to understand the rules your AI is following (a worthwhile ten minutes, but not a prerequisite).
Deterministic selective context
Every one of the 212 skills compiles to a validated Skill Specification v2 contract. For ordinary Markdown use, the canonical SKILL.md remains enough. For agent runtimes, the optional MCP catalog can route a task, require typed inputs, choose an execution mode, and return only the applicable core and modules through get_skill_context.
Selection is fail-closed and inspectable. Missing activation inputs do not load every candidate module. Each bundle includes a decision record for every declared module, per-file SHA-256 hashes, inherited-rule dependency hashes, a compiled-contract fingerprint, token-planning estimates, and a deterministic bundle fingerprint for audit or replay. CI enforces declared context budgets in reports/selective-context.md.
The first two modularized workflows show the model:
litigation/motion-opposition-drafter: mode-based loading for quick triage, standard drafting, and deep verification.ip/infringement-triage: mode-based common modules plus right-specific loading for trademark, copyright, patent, and trade secret matters.
The compact cores are now below the repository's large-context band. Standard scenarios use about 58% of their pre-migration context estimate while preserving the complete deep-review package. These figures are deterministic planning estimates, not provider token counts or billing claims.
Practice areas
AgentCounsel has 212 skills: 177 across 20 practice areas, plus 35 cross-cutting skills in three supporting groups (Setup, Legal Operations, Legal Methodology).
| Practice area | Skills | Covers |
|---|
| Legal Research | 6 | Research planning (roadmap before authority gathering), structured IRAC memos, case briefs, multi-authority rule synthesis, negative-treatment (good-law) checks, and CFR amendment-history tracing. |
| Litigation | 11 | Matter intake, chronologies, demand letters, subpoena triage, discovery-response organization, depositions, legal holds, privilege logs, claim charts, brief drafting, and motion-opposition drafting. |
| Contracts | 5 | NDAs, commercial contracts, redlines, statements of work, vendor agreement status. |
| Corporate | 7 | Board minutes, shareholder-meeting minutes, written consents, closing checklists, diligence review, material-contract schedules, entity compliance. |
| Employment | 10 | Terminations, reductions in force, worker classification, hiring, restrictive-covenant review, internal investigations, protected leave, severance, workplace policies. |
| Privacy | 10 | Data processing agreements, impact assessments, data subject requests, policy gaps, breach and incident response, cross-border transfer review, vendor privacy diligence, data retention schedule review, children's privacy review, and cookie consent review. |
| Product Legal | 4 | Launch review, marketing claims, terms of service, AI features. |
| Regulatory | 5 | Enforcement risk, rule-change summaries, compliance gaps, compliance-program tracking, examination/inquiry response. |
| AI Governance | 4 | AI use-case intake, vendor terms, model risk, AI policies. |
| Intellectual Property | 7 | Trademark triage, infringement triage, cease-and-desist response, patent FTO triage, invention intake, DMCA, open-source licensing. |
| Financial Crime / AML | 5 | KYC onboarding review, sanctions / PEP / adverse-media screening review, transaction-monitoring alert triage, AML program gap review, and EDD file review. |
| Real Estate | 10 | Commercial lease abstraction and review, amendment reconciliation, purchase and sale agreement review, loan-document review, title and survey objection tracking, diligence and closing checklists, estoppel and SNDA review, zoning issue-spotting. |
Three cross-cutting skill groups support work in every practice area:
- Setup (20 skills) — cold-start interviews that configure AgentCounsel for a practice group, plus a matter-workspace builder.
- Legal Methodology (11 skills) — source validation, citation integrity, assumption audit, hallucination red-team, attorney-review gate, privilege/confidentiality review, legal prose polish, output-format compliance, statutory interpretation, risk assessment, and red-team verification.
- Legal Operations (4 skills) — legal intake triage, templated legal responses, meeting briefings, and signature-routing checks.
The four-tier taxonomy that classifies these areas and groups — and the model for expanding it — is recorded in docs/PRACTICE_AREAS.md.
See SKILLS_INDEX.md for the full catalog and WORKFLOW_ROUTER.md to route from a task to a skill.
Choose your workflow
Most tasks are one skill. When the work is larger, AgentCounsel gives you several surfaces:
| Surface | Use it when |
|---|
| One-off skill | A single, self-contained task and one draft output. |
| Quality check | Reviewing an existing draft — source validation, citation integrity, prose polish, red-team. |
| Practice-area pack | Repeated work in one practice area, installed into your AI tool. |
| Matter pack | A recurring matter type that runs an ordered sequence of skills. |
| Matter workspace | A multi-step, document-heavy, deadline- or source-sensitive, ongoing matter. |
| Playbook | A recurring task type you run the same way every time (e.g., NDA review). |
| Review panel | A high-risk draft that needs several supervised review passes before reliance. |
Full decision guide with worked examples: docs/CHOOSE_YOUR_WORKFLOW.md. Every surface ends in attorney review.
How it is organized
core/ Operating rules every skill inherits (read these first).
skills/ The canonical skill library, grouped by practice area.
examples/ Illustrative sample outputs, with fictional facts.
practice-profiles/ Per-practice-area configuration profiles for a legal team.
matter-workspaces/ Scaffolds for organizing one matter — single-file templates
plus the canonical multi-file _template/.
matter-packs/ Workflow bundles — recommended skill sequences per matter type.
playbooks/ Repeatable recipes for recurring task types (NDA review, etc.).
review-panels/ Supervised multi-pass review workflows for a draft.
overlays/ Industry and sector overlays that tune skills for a context.
adapters/ Thin integration files for specific environments.
connectors/ External-source verification integrations (e.g., CourtListener).
metadata/ Generated machine-readable skill index (index.json).
docs/ The metadata standard, the safety model, the FAQ, and the practice-area registry.
scripts/ Standard-library Python helpers (validation, index, packs).
dist/ Generated platform install packs (gitignored; built by
scripts/build_platform_packs.py).
SKILLS_INDEX.md Full catalog of every skill.
WORKFLOW_ROUTER.md "I need to do X" -> which skill to use.
COMMANDS.md Slash-style command shorthands mapped to skills.
The skills/ directory is the canonical source of truth. Everything else points back to it.
Anatomy of a skill
Each skill lives in its own folder with a SKILL.md file and optional templates/:
skills/contracts/nda-review/
SKILL.md The workflow.
templates/nda-risk-table.md A copyable, attorney-review-ready template.
Every SKILL.md follows the same structure — Purpose, Use When, Required Inputs, Do Not Use When, Legal Safety Rules, Workflow, Output Format, and an Attorney Verification Checklist — and carries standardized, agent-readable YAML frontmatter so tools and agents can discover and route skills. See docs/SKILL_METADATA_STANDARD.md.
Ways to use AgentCounsel
Recommended: install a pre-built practice-area pack
A platform pack is one file that bundles the global safety rules, the practice profile, the slash commands, and every skill in a practice area. Upload it to your AI tool's project or workspace and you can start work immediately — no copying files one at a time.
Pre-built packs are hosted on the deployed Pages site and rebuilt on every push to main:
- Browse the packs page — direct downloads per practice area for ChatGPT (.md), Claude (.zip), and Gemini (.zip), plus AGENTS.md / CLAUDE.md for repo agents.
- The packs page lists every practice area with its skill count and a "How to use" block per platform.
For finer-grained control, you can also...
AgentCounsel is plain Markdown, so it works anywhere an agent or person can read a file. The library-as-files paths below give you more control than a consolidated pack.
| Surface | How to use AgentCounsel | Where to look |
|---|
| Generic Markdown | Open any ordinary SKILL.md directly. When a skill has SPEC.json, use the catalog's Copy Full Package action or copy the complete skill folder so its selectable resources remain available. | adapters/generic-md/ |
| ChatGPT | Create a ChatGPT Project and add individual skill files. (For the consolidated practice-area pack, use the packs page above.) | adapters/generic-md/ |
| Claude (claude.ai) | Create a Claude Project and upload a practice-area pack from the packs page — no command line needed. | QUICKSTART.md |
| Claude Code | Use the Claude Code plugin-style bundle, or keep the repo in a folder Claude can read as a local playbook. | adapters/claude-code-plugin/ |
| Claude Cowork | Point Cowork at the repo folder; START_HERE.md gives it the operating model. | adapters/claude-cowork/ |
| Gemini | Install the repository as a Gemini CLI extension — gemini-extension.json and GEMINI.md load the operating model automatically. | adapters/gemini/ |
| Codex / repo agents | Point a repo-based coding or legal agent at the library through AGENTS.md so it selects the narrowest relevant skill. | adapters/codex/, |
Adapters are intentionally thin: they tell an environment how to find and use the canonical library; they do not duplicate it. The one exception is the Claude Code plugin bundle, which carries generated copies of a curated set of skills — regenerate it with python scripts/sync_plugin_skills.py (see PLUGIN_SYNC.md).
Installing or copying skills
- A practice area (recommended): download a pre-built pack from the packs page — one file per practice area for ChatGPT, Claude, and Gemini. Or run
python scripts/build_platform_packs.py locally to produce the same packs in dist/.
- One skill: for an ordinary skill, copy
SKILL.md and any templates. When the folder contains SPEC.json, copy the complete folder or use the catalog's Copy Full Package action; the compact SKILL.md alone is the routing and quick-triage core, not the full standard/deep package.
- The whole library: clone the repository, or vendor
skills/ and core/ into your own project.
There is no required installer or runtime dependency. Ordinary skills remain portable files; modularized skills remain portable Markdown-plus-JSON folders. The MCP server is optional and exists for clients that need typed routing, true selective loading, and reproducible context bundles.
Safety model
Every skill inherits the operating rules in core/:
- Draft legal work product only. Attorney review is always required before output is relied upon.
- Never invent legal authority, citations, quotations, facts, or deadlines.
- Separate facts, assumptions, law, analysis, strategy, and verification items.
- Identify jurisdiction, governing law, posture, and the relevant date — or flag them as unknown.
- Preserve confidentiality and privilege.
- Flag uncertainty with visible placeholders instead of guessing.
The full safety model — the threat model, what AgentCounsel deliberately does not do, and how to use it safely with confidential material — is in docs/SAFETY_MODEL.md. Security reporting and guidance are in SECURITY.md.
A firm's risk or compliance team assessing AgentCounsel for adoption should start with docs/AI_GOVERNANCE_DISCLOSURE.md, which maps these controls to common AI-governance framework questions.
Configuring AgentCounsel for a team
AgentCounsel runs out-of-the-box without configuration. To improve output quality for a practice group adopting the library across multiple matters, you can populate a practice-group profile at practice-profiles/<area>.md. The profile gives ~20 skills access to the group's standing positions, escalation thresholds, and output preferences.
Eval coverage is tracked through lightweight, no-API checks in evals/ and
reports/eval-coverage.md. These evals test structure, routing, metadata,
packs, quality checks, and candidate-output safety signals; they do not verify
legal correctness or replace attorney review.
See CONFIGURING.md for the full configuration guide. The short version:
- Run the cold-start interview for the practice area (
skills/setup/<area>-cold-start-interview/SKILL.md) with a supervising attorney, or edit the profile template directly.
- Load the populated profile into your AI workspace alongside any skill that consumes it (see
practice-profiles/README.md for the list).
- Skills that consume the profile will benchmark against its Standard Positions and Escalation Thresholds; skills that do not consume it are unaffected.
Configuration is opt-in. Skipping it costs you benchmarking-against-standing-positions but does not degrade any other skill's output.
Two optional layers let a legal team adapt the library without changing any skill:
practice-profiles/ — one profile per practice area capturing the team's jurisdictions, escalation thresholds, standard positions, review requirements, and prohibited assumptions. The Setup cold-start interview skills fill a profile in.matter-workspaces/ — scaffolds for organizing one specific matter: parties, documents, deadlines (always flagged for attorney verification), open items, sources, and an index of the draft work product produced by skills. Single-file templates plus a canonical multi-file template at matter-workspaces/_template/, which python scripts/init_matter_workspace.py instantiates. See docs/MATTER_WORKSPACES.md.
Both are plain Markdown and add no backend, runtime, or vendor dependency.
Examples
The examples/ directory contains illustrative sample outputs — including primary skill outputs and quality-layer passes such as source validation, prose polish, hallucination red-team, and attorney-review gating. Every fact in them is fictional. They show the shape and quality of a skill's deliverable; they are not legal advice and not templates for a real matter. If you have not run a skill end-to-end yet, docs/tutorials/practice-matter.md is a guided, fictional first-run walkthrough.
Validation and continuous integration
The repository ships a lightweight validation script — Python standard library only, no dependencies — that checks every skill's structure, frontmatter, links, and safety framing:
python scripts/validate_repo.py
GitHub Actions runs the same checks on every pull request and on pushes to main (see .github/workflows/validate.yml):
python scripts/sync_plugin_skills.py --check # plugin bundle is in sync
python scripts/validate_repo.py # full repository validation
Other standard-library helpers in scripts/ build the machine-readable skill index (build_skill_index.py), the per-platform install packs (build_platform_packs.py), the matter-workspace initializer (init_matter_workspace.py), and the browsable static catalog under site/. Every script is documented in docs/CLI.md; the recommended commands to run after each kind of edit are in docs/AGENT_COMMANDS.md. See VALIDATION.md for the full list of checks.
Platform pack manifests and plugin-compatibility guidance are documented in
docs/PLUGIN_COMPATIBILITY.md. The generated metadata files metadata/index.json, metadata/router.json, metadata/skill_specs.json, metadata/selective_context_metrics.json, and metadata/packs.json are the machine-readable surfaces for skills, routing, typed execution, context budgets, and platform packs.
Contributing
New skills and improvements are welcome. AgentCounsel is Markdown-first and safety-first — see CONTRIBUTING.md for the rules (including how to add skills, quality checks, evals, playbooks, review panels, and packs), docs/SKILL_METADATA_STANDARD.md for the frontmatter standard, and SECURITY.md for security guidance. Questions are answered in docs/FAQ.md.
For the bigger picture, see docs/PROJECT_STATUS.md (an honest maturity snapshot — what is stable, what needs manual review, what is experimental) and docs/WORKFLOW_MAP.md (how core rules, skills, quality checks, packs, workspaces, playbooks, review panels, and evals fit together).
License
MIT License — see LICENSE. Attribution for content adapted from other open-source projects (which remain under their original Apache-2.0 terms) is recorded in THIRD_PARTY_NOTICES.md. AgentCounsel is an independent open-source project and is not affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or Google.
Disclaimer
AgentCounsel is a workflow library — not a law firm and not a lawyer. Using it does not create an attorney–client relationship, and it does not provide legal advice. All output is draft work product that must be reviewed and adopted by a qualified, licensed legal professional before it is relied upon. You are responsible for the use of these materials and for compliance with the rules of professional conduct that apply to you.
