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 alex-alecu/garden-desk --skill legal-due-diligence-reviewgit clone --depth 1 https://github.com/alex-alecu/garden-deskWrote 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/alex-alecu/garden-desk/legal-due-diligence-review)<a href="https://agentmods.dev/skills/alex-alecu/garden-desk/legal-due-diligence-review"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/legal-due-diligence-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/alex-alecu/garden-desk/legal-due-diligence-review"><img src="https://agentmods.dev/badge/skills/alex-alecu/garden-desk/legal-due-diligence-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 | $0.00000 | $0.00248 |
| Opus 5.5 | $0.00000 | $0.00099 |
| Sonnet 5.5 | $0.00000 | $0.00050 |
| Haiku 4.5 | $0.00000 | $0.00025 |
Grade A, and why
legal-due-diligence-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 2mo 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.
What it actually says
Use only supplied document set, request list, playbook, and thresholds. Do not assume jurisdiction, legal requirement, materiality threshold, or missing document.
Map every requested topic to reviewed files and sections. Track complete, partial, missing, unreadable, conflicting, duplicate, and out-of-scope material. Check referenced schedules, exhibits, consents, approvals, amendments, notices, and signature pages. Do not mark a request complete because one related file exists.
For each supported issue, record entity, document, date, parties, subject, exact source fact, supplied threshold, possible effect, and required human check. Keep one issue per row. Keep missing evidence separate from an adverse finding. Do not infer legal effect, validity, breach, control, or ownership.
Output one table: topic; status; source fact; evidence location; supplied threshold; required check. Finish with open requests and parts not reviewed. Require qualified human review before a transaction or legal decision. This skill does not determine legal effect, validity, breach, control, or ownership.
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.
- 2mo ago First seen · 13 lines · 0 tokens per session scan A 26740525c765
legal-due-diligence-review is a skill published in the GitHub repository alex-alecu/garden-desk (6 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 248 tokens. 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 2026-08-31.
legal-due-diligence-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| legal-due-diligence-reviewalex-alecu/garden-desk | Skill | 6 | 1mo ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| auditing-deidentification-runsmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 155 | Claude Code |
| pseudonymizing-for-gdprmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 158 | Claude Code |
| reporting-adverse-eventsmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 195 | Claude Code |
| validating-us-coremaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 134 | Claude Code |
| fda-databasesynthetic-sciences/openscience | Skill | 4.4k | today | Apache-2.0 | A | 43 | Claude Code, Codex |
| setup-openmedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 62 | Claude Code |