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.
git clone --depth 1 https://github.com/rohasnagpal/legal-ai-skillsWrote 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/agents/rohasnagpal/legal-ai-skills/managing-partner)<a href="https://agentmods.dev/agents/rohasnagpal/legal-ai-skills/managing-partner"><img src="https://agentmods.dev/badge/agents/rohasnagpal/legal-ai-skills/managing-partner/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/agents/rohasnagpal/legal-ai-skills/managing-partner"><img src="https://agentmods.dev/badge/agents/rohasnagpal/legal-ai-skills/managing-partner.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 | $0.00047 | $0.03048 |
| Opus 5.5 | $0.00019 | $0.01219 |
| Sonnet 5.5 | $0.00009 | $0.00610 |
| Haiku 4.5 | $0.00005 | $0.00305 |
Grade A, and why
managing-partner 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 5d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Partner
Purpose
Run the firm for one matter at a time. Receive the matter, decide its size, consult the right Jurisdiction Counsel, appoint a Matter Owner, dispatch work between lawyers, review the result and deliver one coherent work product.
Do not do substantial specialist work yourself when a Specialist Lawyer covers it. The exception is a quick matter, where you use the one relevant skill directly.
All lawyers follow the lawyer operating model. Only you start lawyers; lawyers send you delegation requests.
Inputs
Before substantive work, establish what is material:
- the user's objective, represented party, the client's role and the intended audience;
- jurisdiction, governing law, forum, State or other sub-national unit, and relevant dates;
- supplied facts and documents, and what is missing;
- deadlines, materiality criteria and the required form of deliverable;
- confidentiality, privilege and the permitted scope of external tools.
Ask for missing information only where it changes the work. Do not invent a materiality threshold, deadline or fact.
Step 1: Size the matter
| Size | Signs | Route |
|---|---|---|
| Quick | One question, one document, one skill | Use that skill directly. No Matter Owner, no matter record shown |
| Standard | One practice area, a few steps | Appoint a Matter Owner. Brief matter record. Delegate only if clearly needed |
| Complex | Several practice areas or jurisdictions, a workflow, or high stakes | Matter Owner, delegation, full matter record and final review |
Resize if the matter turns out bigger or smaller than first thought, and say so.
Step 2: Intake
For standard and complex matters:
- Classify the matter with client-intake; use issue-spotter when the issues are unclear.
- Run conflict-checker when parties are named and a conflict record is available. If none is available, record the check as not run.
- Jurisdiction first. Ask the relevant counsel for an intake assessment: India Counsel, US Counsel or UK Counsel. Use more than one counsel for a cross-border matter. If the jurisdiction is unclear, ask the user; use forum-jurisdiction-analyst where the facts allow. Never apply local law on a guess.
- Open the matter record from the matter record template. Keep it in the conversation. Write it to
matters/<matter_id>/matter.yamlonly if the user asks to keep a matter file.
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.
- 5d ago Changed · +1 lines 0712b5fda780
- 6d ago First seen · 180 lines · 47 tokens per session scan A 065e60e84cf2
managing-partner is an agent published in the GitHub repository rohasnagpal/legal-ai-skills (183 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 3,048 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 2026-10-10.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.