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 severance-reviewgit 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/severance-review)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/severance-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/severance-review/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/severance-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/severance-review.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 | $0.00037 | $0.02982 |
| Opus 5 | $0.00018 | $0.01491 |
| Sonnet 5 | $0.00007 | $0.00596 |
| Haiku 4.5 | $0.00004 | $0.00298 |
Grade A, and why
Severance Review 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 10d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Severance Review
Purpose
Produce a structured, attorney-ready review of a severance or separation agreement. The skill identifies the key provisions, assesses their scope and risk from the perspective of the indicated party, flags claims that may not be waivable and statutory requirements that must be confirmed, and surfaces issues for attorney resolution. This is draft legal work product — not legal advice.
Use When
- A user asks to "review this severance agreement" or "what am I giving up if I sign this?"
- An employee or employer has received a proposed separation agreement and needs a first-pass structured review.
- Counsel needs a provision-by-provision issues list to begin their own analysis.
- A user wants to understand what claims a release covers before agreeing or rejecting.
- The user phrases it as: "help me understand what this says," "is this a good deal," or "what should we look at before signing?"
Required Inputs
- The full agreement text: uploaded or pasted. Do not review from a description — the actual document text is required.
- Reviewing party: employee/departing worker or employer/company. The analysis will be framed from this party's perspective.
- Jurisdiction: the state, province, or country whose law governs the agreement, or flag as unknown.
- Employee age: confirm whether the employee is age 40 or over, as this affects statutory disclosure and timing requirements. If unknown, flag for attorney confirmation.
If the agreement text is not provided, stop and request it. Do not summarize, analyze, or opine on an agreement that has not been provided.
Do Not Use When
- The document is a general employment contract rather than a severance or separation agreement (use
contract-risk-reviewor a general contract review skill). - The termination has not yet occurred and the question is whether to proceed with it (use
termination-risk). - The user is asking whether a particular claim is legally viable or what damages they might recover — those questions require legal advice from counsel, not this skill.
- The user wants to draft a severance agreement from scratch rather than review an existing one (a separate drafting skill applies).
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.
- 10d ago First seen · 146 lines · 37 tokens per session scan A 1411b1c800ef
Severance Review is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,982 once invoked, about $0.0002 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
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.
redline-sentry
Review NDAs, MSAs, DPAs, SaaS agreements, and other procurement contracts against a configurable risk playbook. Use whenever the user drops a contract file (PDF, DOCX) and asks to redline, review, summarise risk, check clauses, or "what would procurement say". Trigger on phrases like "review this NDA", "redline this…
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…
eu-cra
Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability handling requirements for all products with digital elements (PDEs) sold in the EU. Use this skill for gap analysis, product classification (Default / Class I / Class II), conformity assessment route…