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-holdgit 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-hold)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/legal-hold"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/legal-hold/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-hold"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/legal-hold.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 | $0.00046 | $0.03152 |
| Opus 5 | $0.00023 | $0.01576 |
| Sonnet 5 | $0.00009 | $0.00630 |
| Haiku 4.5 | $0.00005 | $0.00315 |
Grade A, and why
Legal Hold 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Hold
Purpose
Produce a structured draft litigation hold notice and preservation-scope summary for attorney review. The skill supports three modes: issue (a new hold), refresh (update scope, custodians, or date range on an existing hold), and release (lift a hold when the matter closes). It organizes the preservation scope, identifies custodians and the systems they use, flags departed custodians whose data requires system-level preservation, and drafts a notice that communicates clearly to recipients what they must preserve, how, and why. It does not decide whether a duty to preserve has been triggered — that is a legal determination the attorney must make before this skill is used. The draft notice must not be distributed to custodians without attorney review and approval.
Use When
- An attorney has determined that a duty to preserve has been triggered and needs a first-draft hold notice to send to custodians.
- A prior hold must be refreshed because the scope has changed, additional custodians have been identified, the date range has expanded, or new systems are in scope.
- A matter has closed and counsel needs a draft hold-release notice confirming that preservation obligations have lifted.
- The attorney wants a preservation-scope summary alongside the notice to document what was covered and why.
Required Inputs
For all modes:
- Matter identification — name, number, or brief description sufficient to identify the matter.
- Trigger event — the event that prompted the hold (e.g., receipt of a complaint, a threat of litigation, a regulatory inquiry). The attorney must have already determined that this event triggers a preservation duty; this skill does not make that determination.
- Preservation scope — the categories of documents, communications, and data to be preserved (e.g., contracts, correspondence, financial records, project files, metadata).
- Named custodians — the individuals who may possess responsive information, with their roles or titles. Identify any departed custodians separately.
- Date range — the start date and end date (or "ongoing") for responsive material. The attorney must supply these dates; this skill does not compute or assert a trigger date.
- Systems in scope — the platforms, applications, and devices from which material must be preserved (e.g., email, chat and messaging tools, file-share and cloud-storage platforms, devices, CRM systems, legacy or archival systems, voicemail).
- Effective date of the hold — the date on which the preservation obligation begins. Provided by the attorney; do not compute.
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.
- 9d ago First seen · 157 lines · 46 tokens per session scan A a74b5212bd43
Legal Hold is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 3,152 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 2026-09-03.
Other skills, from other repositories
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.
change-order-manager
Manage construction change orders from request to approval. Track costs, schedule impacts, and maintain audit trail for dispute prevention.