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 deal-negotiationgit 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/deal-negotiation)<a href="https://agentmods.dev/skills/cbrock84/headcount/deal-negotiation"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/deal-negotiation/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/deal-negotiation"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/deal-negotiation.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 | $0.01124 |
| Opus 5.5 | $0.00036 | $0.00450 |
| Sonnet 5.5 | $0.00018 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
deal-negotiation 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deal negotiation
Most deals are lost or discounted before the negotiation starts, in the preparation that did not happen. By the time you are trading, your position is largely fixed.
Prepare three numbers and one alternative
- Your target — what a good outcome looks like, set before the conversation and not adjusted because it is late in the quarter.
- Your walk-away — the point below which no deal is better than this deal. Write it down in advance, because it will not survive being decided in the room.
- Your best alternative if this does not close. The strength of your position comes almost entirely from this, and a full pipeline is what makes a walk-away credible rather than a bluff.
- Their alternative, honestly assessed. A buyer with no other viable option and a deadline is in a weaker position than their behavior suggests, and a buyer who genuinely prefers a competitor is in a stronger one than yours.
Understand what they are actually optimizing for
The stated ask is rarely the real constraint. "We need 20% off" is often a budget that was set before the scope, a fiscal calendar, an approval threshold they want to stay under, or a person who needs to be seen negotiating.
Ask what is driving the number. A budget ceiling has several solutions — payment timing, term length, a smaller starting scope — and only one of them is discount.
Trade, never concede
Every concession buys something. A discount buys a longer term, a case study, a faster payment schedule, a reference, or narrower scope. A concession given for nothing teaches the other side that pushing works, and there is always another push.
Concede in decreasing increments. Movements that stay the same size or grow signal that more remains. Small and shrinking signals you are at the end, and it does so more credibly than saying so.
Protect price by moving other variables
Price is the most visible term and the most permanent — it sets the reference for the renewal and, once it leaks, for the next customer. Where you have room, prefer to move term length, scope, payment timing, support tier, or ramp.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +7 lines cba5f3b6deba
- 1mo ago First seen · 92 lines · 91 tokens per session scan A 4081140905fc
deal-negotiation is a skill published in the GitHub repository cbrock84/headcount (2,081 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 1,124 once invoked, about $0.0004 per session on Opus 5.5. 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
rotate-creative
Pause fatigued ads and ship fresh creative variants in their place. Works on both Meta and Google Ads. Use when CTR is dropping, frequency is climbing, or the user says "creative is tired" / "let's refresh ads". Always starts new variants paused.
launch-google-search
Launch a complete Google Ads Search campaign — campaign, ad group, responsive search ads, keywords, sitelinks, callouts, and negatives — built paused and ready to review. Use when the user wants to spin up a new Search campaign on Google Ads.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
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.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.