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 red-team-verifiergit 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/red-team-verifier)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/red-team-verifier"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/red-team-verifier/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/red-team-verifier"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/red-team-verifier.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 | $0.00072 | $0.04186 |
| Opus 5 | $0.00036 | $0.02093 |
| Sonnet 5 | $0.00014 | $0.00837 |
| Haiku 4.5 | $0.00007 | $0.00419 |
Grade A, and why
Red-Team Verifier 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 9d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red-Team Verifier
Purpose
Adversarially stress-test a legal work product before anyone relies on it. This is AgentCounsel's universal quality-control workflow: it applies to any legal output — a memo, a contract or document review, a demand letter, a risk matrix, a client email, a research summary, a draft filing, or any other analysis — whether the output was produced by an AgentCounsel skill, another AI tool, or a person.
The skill conducts a systematic, category-by-category challenge pass across the draft, hunting for: invented or unverifiable authority; unsupported legal and factual claims; unstated jurisdiction and unverified timing; hidden assumptions and missing facts; weak or incomplete legal reasoning; professional-responsibility problems (language that reads as legal advice, lost attorney-review framing, confidentiality and privilege exposure); confidence overstatement; and structural defects. It produces a verification findings report — a structured set of defects with severity ratings and recommended fixes — plus an overall PASS / REVISE verdict.
It produces draft legal work product for attorney review. It is not legal advice, and a PASS verdict is not a substitute for attorney review.
Use When
- The user asks to check, sanity-check, or quality-control a legal memo, a contract or document review, a demand letter, a legal analysis, a risk matrix, a client email, a research summary, or a draft filing.
- The user asks "is this good enough?", "is this ready to send?", or "can I rely on this?"
- The user asks for the weaknesses, blind spots, or missing issues in a legal draft.
- The user asks for a hallucination check, a citation check, or a check for invented authority.
- The user asks whether a draft is ready for — or has been adequately prepared for — attorney review.
- Any AgentCounsel skill has produced a draft and a defect check is warranted before it is finalized or relied upon.
- A high-stakes legal output is about to be sent, filed, or acted on and a final adversarial pass is wanted.
- A draft has been revised and a targeted re-check of the changed sections is needed.
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.
- 9d ago First seen · 210 lines · 72 tokens per session scan A 43b98ce5f5bb
Red-Team Verifier is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 4,186 once invoked, about $0.0004 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
claim-verification-checklist
Generates a point-by-point checklist of every verifiable claim in a draft article, categorized by claim type and accompanied by the specific evidence needed to confirm each one.
gdpr-dsgvo-expert-neekware
GDPR and German DSGVO compliance automation. Scans codebases for privacy risks, generates DPIA documentation, tracks data subject rights requests. Use for GDPR compliance assessments, privacy audits, data protection planning, DPIA generation, and data subject rights management.
mk:qa
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a…
mk:lint-and-validate
Automatic quality control, linting, and static analysis after code modifications. Triggers on: lint, format, check, validate, types, static analysis. NOT for full build verification (see mk:verify); NOT for test coverage (see mk:testing).
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.