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 Buildwise-Studios/claude-for-hk-law --skill internal-investigationgit clone --depth 1 https://github.com/Buildwise-Studios/claude-for-hk-lawWrote 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/buildwise-studios/claude-for-hk-law/internal-investigation)<a href="https://agentmods.dev/skills/buildwise-studios/claude-for-hk-law/internal-investigation"><img src="https://agentmods.dev/badge/skills/buildwise-studios/claude-for-hk-law/internal-investigation/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/buildwise-studios/claude-for-hk-law/internal-investigation"><img src="https://agentmods.dev/badge/skills/buildwise-studios/claude-for-hk-law/internal-investigation.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 | $0.00079 | $0.06385 |
| Opus 5 | $0.00039 | $0.03193 |
| Sonnet 5 | $0.00016 | $0.01277 |
| Haiku 4.5 | $0.00008 | $0.00639 |
Grade A, and why
internal-investigation 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 11d 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 — 766 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Internal Investigation Skill
Matter context
Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗ (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /employment-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-hk-law/employment-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.
Output header
Prepend the work-product header from ~/.claude/plugins/config/claude-for-hk-law/employment-legal/CLAUDE.md → ## Outputs (it differs by user role — see ## Who's using this). Every file, log, memo, and summary produced by this skill opens with that header.
Distribution discipline. Every file this skill creates — log entries, memo drafts, audience summaries, document notes — inherits the privilege and confidentiality status of the underlying investigation. Distribution beyond the privilege circle (forwarding to non-attorneys outside the investigation team, cc'ing HR without scoping, handing to the business side) can waive privilege over the entire investigation. Store these files where privileged materials live, label per the work-product header, and make every distribution decision deliberately.
⚠️ Privilege notice — read before proceeding
Marking does not create privilege. The header above reflects the intended protection and is important to include — but it does not itself establish privilege. Whether any given output is actually privileged depends on whether the investigation is attorney-directed, the purpose for which documents are created, and how they are subsequently used or disclosed.
Before opening a matter, confirm: Is this investigation attorney-directed? If it is not — if HR is running it with legal in an advisory role, or if it was not initiated at the direction of counsel for the purpose of obtaining legal advice — the privilege analysis changes materially and this skill's default labeling may be misleading. Flag that question to the attorney before creating any log or file.
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.
- 11d ago First seen · 766 lines · 79 tokens per session scan A 8b6d5d9eaf58
internal-investigation is a skill published in the GitHub repository Buildwise-Studios/claude-for-hk-law (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 6,385 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 2026-08-31.
Other skills, from other repositories
c2pa-metadata
Embed a C2PA provenance manifest into an AI-generated marketing asset (PNG, JPG, WebP, GIF, TIFF, MP4, MOV, WebM, MP3, WAV, PDF) via scripts/embed-c2pa.py — produces a signed copy of the file carrying IPTC digital-source-type AI claims, an optional c2pa.ai-disclosure assertion for EU AI Act Article 50 (applicable 2…
privacy-jp
A Japanese-language document generator for services built with Next.js. It creates privacy policies, terms of service, consent dialogs, and cookie banners while considering Japan's personal-information and consumer-protection laws.
revenue-recognition
Determines when and how revenue is recognized — performance obligations, contract terms that change the answer, and the deal structures that create accounting problems. Use this to work out how a contract should be recognized, review a non-standard deal before it is signed, understand deferred revenue, or spot terms…
contract-review
Reviews and negotiates commercial agreements — MSAs, SOWs, order forms, NDAs, vendor and data-processing agreements — identifying material risk, proposing positions, and recommending a path rather than listing issues. Use this to review a contract before signature, prepare a negotiation position, build fallback…
privacy-and-data-protection
Assesses and improves how personal data is collected, used, shared, and retained — data mapping, lawful basis, consent, processor agreements, subject rights, and breach obligations. Use this before launching anything that handles personal data, when adding a vendor that will process it, when a data subject request…
benefits-and-leave
Designs and runs employee benefits and leave — health and retirement plans, leave policy, cost and renewal, and the administration that keeps them compliant. Use this to design or review a benefits package, prepare for a renewal, write leave policy, handle a leave request, or decide what benefits are worth their cost.