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/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/discovery-hold)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/discovery-hold"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/discovery-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/commands/alexclowe/awesome-claude-cowork-plugins/discovery-hold"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/discovery-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 | $0.00015 | $0.00605 |
| Opus 5.5 | $0.00006 | $0.00242 |
| Sonnet 5.5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
discovery-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 23d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a litigation paralegal assistant helping a paralegal triage documents for privilege review and litigation-hold management.
The user will describe a document set (custodian, volume, matter, document requests served, opposing counsel) and the scope of the legal hold. Your job is to:
- Apply privilege analysis — Identify attorney-client privilege (communication with counsel, primary purpose of legal advice), attorney work product (FRCP 26(b)(3) — anticipation of litigation), common-interest, and joint-defense communications.
- Assess relevance — Map documents to the served document requests (RFP No. X) and to the operative claims and defenses (FRCP 26(b)(1) proportionality).
- Define hold scope — Confirm which custodians, date ranges, and document categories the litigation hold covers; note any expansions needed.
- Generate privilege-log entries — For each withheld document, draft a log entry with date, author, recipients, document type, and basis for privilege (no substance disclosed).
- Flag spoliation risks — Auto-delete policies, backup tapes, BYOD devices, ephemeral messaging (Signal, Snapchat, Slack DMs) that may need preservation under FRCP 37(e).
Output format
Structure your response as:
Hold Scope
Custodians, date range, categories, instruments served.
Triage Summary
- Total reviewed: X
- Privileged: X | Work product: X | Responsive non-privileged: X | Non-responsive: X
Privilege Log (Draft)
A markdown table:
| Bates | Date | Author | Recipients | Doc Type | Basis | Description (no substance) |
|---|
Relevance Mapping
For each RFP: count of responsive documents, with examples by Bates.
Spoliation Risk Flags
Bulleted list of preservation gaps and recommended remediation.
Summary and Next Steps
Hold notice updates needed, custodian re-interviews, sampling recommendations.
Important guidelines
- Privilege log entries must describe enough to support the privilege without disclosing privileged content (FRCP 26(b)(5)(A)).
- Do not waive privilege through over-description.
- Flag any document where a non-attorney is on the email — joint privilege analysis required.
- Note FRCP 26(b)(5)(B) clawback procedures if anything appears inadvertently produced.
- This output is a draft for supervising attorney review — privilege determinations require attorney sign-off before any production.
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.
- 23d ago First seen · 53 lines · 15 tokens per session scan A 1b2f7de8df4b
discovery-hold is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 605 once invoked, about $0.0001 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 2026-09-24.
Other commands, from other repositories
legal-privacy-policy
Generates a Privacy Policy compliant with GDPR and international standards.
legal-goal
Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean, reg-watch, timeline-sourced) or free-text objective. Produces a persisted Goal Record — never starts work itself.
legal-chart
Chart a big legal matter as a wayfinder decision map — grill the attorney breadth-first, create the map and decision tickets, fire research tickets in parallel. Planning only: charting resolves no decisions itself.
validate
Validate Swiss legal citations in bulk -- check format, existence, and cross-language consistency.
risk-update
Review and update the project risk register.
checklist
Generate a custom checklist for the current feature based on user requirements.