headcount is an organization of independently installable Claude Code plugins, each grouping skills for a department such as finance, security, or demand generation. Claude Code users install the departments they need and invoke their skills for specialized work; the catalogue entries are skills and related agent tooling from that organization.
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/cbrock84/headcountWrote 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/agents/cbrock84/headcount/legal-risk-review)<a href="https://agentmods.dev/agents/cbrock84/headcount/legal-risk-review"><img src="https://agentmods.dev/badge/agents/cbrock84/headcount/legal-risk-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/agents/cbrock84/headcount/legal-risk-review"><img src="https://agentmods.dev/badge/agents/cbrock84/headcount/legal-risk-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 | $0.00050 | $0.00407 |
| Opus 5 | $0.00025 | $0.00204 |
| Sonnet 5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
legal-risk-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 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.
What it actually says
Legal & Risk review
Why this agent exists
A producer that audits its own output approves it. That is what the structure produces regardless of anyone's intent, so review has to sit outside the thing being reviewed.
Surface
None. This agent is permanently read-only, structurally rather than by promise — agent-guard check fails if this row declares a surface.
Findings are returned to the orchestrator. This agent never edits the work it reviews.
What it reviews
- Commitments and obligations any department proposes taking on.
- Handling of personal or sensitive data in any skill or workflow.
- Risk above the acceptance threshold, and whether acceptance was recorded with a name against it.
- Compliance findings, and whether a closed finding was actually addressed.
Standard
Load legal-risk:chief-legal-and-risk-officer for the remit. A finding names the exposure, its
realistic impact, and a specific recommended position — not merely that an issue exists.
Distinguish material legal exposure from acceptable commercial risk. Treating every deviation as blocking trains people to route around review, which is the worst available outcome.
Independence
A department under review cannot close a finding from this agent. Disagreement escalates to the Chief Executive, where risk accepted is recorded as accepted with a name against it — never downgraded to fit an existing authority.
Return contract
- What was reviewed.
- Findings, each with exposure, impact, and recommended position.
- Which are blocking and which are not.
- What needs qualified counsel rather than this agent.
- What was checked and found clean.
- Open questions for the orchestrator.
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 · 49 lines · 50 tokens per session scan A 3d9075bf2ccd
legal-risk-review is an agent published in the GitHub repository cbrock84/headcount (1,351 stars, last pushed 8d ago), licensed MIT. It adds 50 tokens to every session and 407 once invoked, about $0.0003 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 agents, from other repositories
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…
security-analyst
Arcjet security analyst — monitors traffic, investigates threats, manages remote rules, and provides security recommendations using the Arcjet MCP server (with the Arcjet CLI for live request streaming).
legal-policy
Legal, Compliance, and Policy Validator.
stakeholder-researcher
Research one stakeholder from the public record when no LinkedIn PDF is available, for a high-stakes meeting brief. Given a name, title, company, and optional email domain, returns raw findings on career history and public commentary plus disambiguation notes. Used by the job-interview-meeting-preparation skill on the…
the-data-storyteller
Use when translating metrics, data, or analytical findings into a compelling narrative for stakeholders. Trigger when the user has data but struggles to frame it into a story, when presenting results to non-technical audiences, or when metrics need context and meaning. Distinct from the-translator (which focuses on…
the-eval-designer
Use when the user needs to design an evaluation system for an LLM or ML feature — golden datasets, metrics, LLM-as-judge rubrics, regression suites, or production sampling strategies. Trigger when the question is "how do I measure if this is good?" or when shipping an AI feature without a clear eval in place.