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 legal-intake-triagegit 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/legal-intake-triage)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/legal-intake-triage"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/legal-intake-triage/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/legal-intake-triage"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/legal-intake-triage.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 | $0.00065 | $0.03070 |
| Opus 5 | $0.00032 | $0.01535 |
| Sonnet 5 | $0.00013 | $0.00614 |
| Haiku 4.5 | $0.00006 | $0.00307 |
Grade A, and why
Legal Intake Triage 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 8d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Intake Triage
Purpose
Produce a structured, review-ready intake triage for an inbound business request to the legal team — the legal front door. The skill classifies the request against the library's practice areas, captures the requester and business context, records urgency and dates exactly as the requester stated them, identifies the matter's gates (jurisdiction, parties, documents in hand) or flags them unknown, surfaces conflict-check and confidentiality considerations as questions, and proposes a routing recommendation — which practice area, which AgentCounsel skill or workflow, and whether the request is self-serve, needs lawyer review, or needs escalation. The output is an intake record ready to paste into a matter or ticketing system.
This skill provides workflow discipline and structure. It produces draft work product for review. This is not legal advice. The skill recommends routing; a human on the legal team decides where the request goes and who handles it.
Use When
- An inbound request reaches the legal team by email, ticket, intake form, or chat — "can legal look at this?", "we need a contract reviewed", "is this okay to send?", "who handles this?"
- A legal ops or triage owner needs a consistent, structured first-pass record before a request is assigned.
- A request's practice area, urgency, or right owner is unclear and a classification pass would help the team route it.
- The team wants every inbound ask logged in the matter system with the same fields every time.
- A request has bounced between owners and needs a clean intake record before anyone works it.
Required Inputs
- The request as received: the full text of the email, ticket, form submission, or chat message — pasted or uploaded. Do not triage from a second-hand summary when the original is available.
- Requester context: the requester's name, team or business unit, and role, to the extent the request or the user supplies them.
- Urgency and dates as stated: whatever the requester said about timing — a requested turnaround, a launch date, a signature deadline, a "need by." These are captured exactly as stated; this skill never computes or validates a deadline.
- Optional: attached or referenced documents — a contract, a marketing asset, a vendor form, a policy. Note which referenced documents are in hand and which are missing.
- Optional: the team's routing conventions — an intake form, assignment rules, or matter-system fields, so the record matches what the team already uses.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 144 lines · 65 tokens per session scan A 73f48bbca66d
Legal Intake Triage is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 3,070 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
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'.
performance-management
Runs performance systems that change behavior — expectations, feedback, review cycles, calibration, and handling underperformance. Use this to design or fix a review process, run calibration, write or coach on feedback, address sustained underperformance, or work out why reviews consume weeks and change nothing.
vendor-evaluation
Evaluate, select, and contract with vendors and SaaS tools. Use this skill when comparing alternatives, running an RFP, scoring vendors against criteria, negotiating contracts, planning a switch, or assessing a vendor's risk. Triggers on vendor evaluation, RFP, vendor selection, build vs buy, SaaS evaluation, vendor…
compliance-tracker
Track regulatory compliance for construction projects. Monitor permits, certifications, inspections, and regulatory requirements with automated alerts and reporting.
safety-inspection-checklist
Digital safety inspection checklists for construction sites. Generate, conduct, and track safety inspections with automated reporting and compliance monitoring.
delay-analysis
Analyze construction schedule delays for claims and recovery. Perform time impact analysis, identify delay causes, calculate damages, and document for disputes.