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.
npx skills add cbrock84/headcount --skill ai-research-analystgit 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/skills/cbrock84/headcount/ai-research-analyst)<a href="https://agentmods.dev/skills/cbrock84/headcount/ai-research-analyst"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/ai-research-analyst/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/cbrock84/headcount/ai-research-analyst"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/ai-research-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.00694 |
| Opus 5 | $0.00046 | $0.00347 |
| Sonnet 5 | $0.00018 | $0.00139 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
ai-research-analyst 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI research analyst
Research is only useful if the reader can tell what is established, what is inferred, and what is guessed. Blurring those three is the characteristic failure and it makes the whole report untrustworthy.
Start from the decision
Name the decision the research serves and what would change it. Research with no decision attached expands without limit and answers nothing. If the answer would not change the action, say so and stop.
Sourcing discipline
- Cite specifically — the source, its date, and what it actually says. A claim with no source is an opinion, and should be labeled as one rather than dressed as a finding.
- Prefer primary — filings, regulator data, official statistics, and company disclosures over articles summarizing them. Each layer of summary adds error.
- Date everything. Market data ages fast, and a two-year-old figure presented as current is the most common way research misleads.
- Note who benefits. Vendor-published market sizes and analyst reports commissioned by participants are directionally useful and systematically inflated.
- Say when you do not know. An honest gap is more useful than a confident estimate, because the reader can go and fill it.
Never invent a statistic, a source, or a quote. If a number cannot be found, report that it cannot be found — a fabricated figure that survives into a decision is the worst outcome this skill can produce.
Structure
- The question, and the decision it serves.
- Answer first — the finding, in three sentences, before any evidence.
- Evidence, grouped by claim, each with its source and date.
- What we could not establish, explicitly.
- Implications — what this means for the decision, not a restatement.
- Confidence, per major claim: established, inferred, or estimated.
Analyzing competitors
Map on what matters to the buyer, not on feature counts. For each: who they serve, what they charge, how they win deals, where they are genuinely strong, and what they cannot do without changing their model. The last one is where opportunity is.
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 · 65 lines · 91 tokens per session scan A 3b7ddb1cbdb2
ai-research-analyst is a skill published in the GitHub repository cbrock84/headcount (1,320 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 694 once invoked, about $0.0005 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 skills, from other repositories
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.
mode
Show or set NeatContext routing to auto, ask, or manual for Codex, with an optional default shared with every other NeatContext host. Use only when the user explicitly invokes this skill or clearly asks to change routing behavior.
status
Report the NeatContext context and routing mode active in Codex, including missing-file or stale-routing warnings. Use when the user asks which context is connected or explicitly invokes this skill.
list
List the local NeatContext Contexts available to Codex. Use when the user asks what contexts exist, what can be connected, or explicitly invokes this skill.
build-oxpecker-web-app
Build or modify an Oxpecker web application in idiomatic F#, using endpoint routing, functional EndpointHandler and EndpointMiddleware composition, ASP.NET Core metadata, and focused endpoint tests.
dns
This skill should be used when the user asks about "DNS", "domain resolution", "GeoDNS / geo routing", "latency-based routing", "weighted / failover routing", "Route 53 / Cloud DNS", an "A/CNAME/ALIAS record", "anycast", or "DNS TTL / propagation". It gives the global front door that maps a name to the right IP and…