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 information-sharing-clean-team-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/information-sharing-clean-team-review)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/information-sharing-clean-team-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/information-sharing-clean-team-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/information-sharing-clean-team-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/information-sharing-clean-team-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 | $0.00080 | $0.02492 |
| Opus 5 | $0.00040 | $0.01246 |
| Sonnet 5 | $0.00016 | $0.00498 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
Information Sharing Clean Team 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 12d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Information Sharing Clean Team Review
Purpose
Review a proposed exchange of competitively sensitive information between actual or potential competitors — in M&A diligence, a JV, benchmarking, a trade association, or a supply negotiation — item by item. Each information item is inventoried with its granularity, age, frequency, recipients, and purpose; flagged high/medium/low sensitivity with a descriptive rationale; and tested against the clean-team design, control gaps, and carryover/spillover risks. The output is a draft for attorney review: the skill never authorizes any exchange and never concludes an exchange is lawful.
Use When
- An M&A counterparty's diligence request list asks for current pricing, customer-level, or capacity data and the deal team wants to know what can go into the data room.
- A clean-team agreement is being set up — or is already operating — and its membership, NDA scope, segregation, and carryover restrictions need testing.
- A proposed JV or collaboration includes data-sharing annexes that would put competitor data into the parties' hands.
- A benchmarking exercise, industry survey, or shared vendor/consultant would pool competitively sensitive inputs from competing companies.
- A supplier-customer negotiation between parties who also compete drifts into requests for cost, capacity, or wage data.
- Counsel asks which proposed data items are high-sensitivity and what controls the exchange currently lacks.
Required Inputs
- Jurisdiction(s) of competitive effect — every country and, where relevant, state/province where the parties operate and the information flow would have effects, or
[verify jurisdiction]. - Context for the exchange — M&A diligence, JV, trade association, benchmarking, supply-chain reasonableness, settlement, or other. Mark unknowns
unknown/not found/not provided/ambiguous. - Parties' competitive posture — actual / potential / no competition, per product market.
- Information categories proposed for exchange — pricing (current, future, list, transaction), costs, customer-specific terms, capacity, output, market shares, wages/hiring, future plans, R&D roadmaps, bid information, customer-level data, sensitive supply terms.
- Data attributes per item — granularity (individual vs. aggregated; identified vs. anonymized), age (historical vs. current/forward-looking), frequency, recency.
- Recipients per item — clean-team-only? counsel-only? designated business individuals? executives? full deal team?
- Controls in place — clean-team agreement, NDA, segregation from competitive decision-makers, retention/destruction protocol, post-deal carryover restrictions, audit.
- Purpose and necessity for each category — what business question the data is meant to answer, and whether less-sensitive alternatives would suffice.
- Documents and source anchors — clean-team agreement, NDA, diligence requests, request list, data-room logs, communications.
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.
- 12d ago First seen · 123 lines · 80 tokens per session scan A fcf06e562e10
Information Sharing Clean Team Review is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,492 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 2026-08-30.
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.
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…
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.