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 agentmods add skills/cbrock84/headcount/outbound-prospectingnpx skills add cbrock84/headcount --skill outbound-prospectinggit 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/outbound-prospecting)<a href="https://agentmods.dev/skills/cbrock84/headcount/outbound-prospecting"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/outbound-prospecting.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.00778 |
| Opus 5 | $0.00037 | $0.00389 |
| Sonnet 5 | $0.00015 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
outbound-prospecting 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outbound prospecting
Reply rates are set by list quality far more than by copy. Most outbound problems are targeting problems being solved as writing problems.
Build the list before writing anything
Define the qualifying signal — the observable fact that means this account probably has the problem you solve, right now. Hiring for a role, using a specific tool, a recent funding or expansion announcement, a public complaint about the thing you fix.
Without a signal you are sending to a demographic, and a demographic has no reason to reply.
Then qualify each account against: do they have the problem, can they afford it, can this person act, and is there a reason for now. Missing the last one is why good-fit prospects go quiet.
Writing
- Under a hundred words. Longer gets skimmed and deleted.
- Open with the signal, specifically. Show you looked. Generic personalization tokens are worse than none — they signal automation while pretending otherwise.
- One problem, in their language, not your feature.
- Ask for something small. A specific question or a fifteen-minute call. "Interested in learning more" asks the recipient to do the work of defining the next step.
- No attachments, minimal links in a first message. Both hurt deliverability and trust.
Sequencing
Three to five touches over two to three weeks. Each one adds something new — a different angle, a relevant case, a useful resource. Never "just bumping this to the top of your inbox," which communicates that the first message was not worth reading either.
Multi-channel works when the channels are coordinated and the sender is a person. It reads as harassment when the same message arrives everywhere at once.
Stop after the sequence ends. Persistence past that converts nothing and costs reputation.
Deliverability
Domain warmed, authentication configured, volume per mailbox kept low, list validated. A technically broken send makes perfect copy irrelevant, and the damage to a sending domain takes months to repair.
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.
- 2d ago First seen · 75 lines · 74 tokens per session scan A cafed49accef
outbound-prospecting is a skill published in the GitHub repository cbrock84/headcount (1,247 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 778 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 2026-09-03.
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…