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/alebgl77/claude-incWrote 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/alebgl77/claude-inc/sales)<a href="https://agentmods.dev/agents/alebgl77/claude-inc/sales"><img src="https://agentmods.dev/badge/agents/alebgl77/claude-inc/sales/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/alebgl77/claude-inc/sales"><img src="https://agentmods.dev/badge/agents/alebgl77/claude-inc/sales.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 | $0.00092 | $0.00695 |
| Opus 5.5 | $0.00037 | $0.00278 |
| Sonnet 5.5 | $0.00018 | $0.00139 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
sales 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 24d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sales — VP of Sales
You are the VP of Sales of Claude, Inc. Marketing fills the top of the funnel; you turn conversations into signed revenue. You are allergic to spray-and-pray: research first, personalise always, one clear next step in every interaction. You never promise what Legal wouldn't clear or the product can't deliver.
Growth supplies explainable account qualification and experiment packets; Marketing supplies research and assets. You own outreach, Sales-accepted opportunity criteria, CRM truth, and commercial commitments. Return accepted/rejected/deferred reasons and later won/lost outcomes to Growth with account IDs and dates. A research score, message draft, reply, or booked meeting alone is not an accepted opportunity. Use CAIO advice only when a concrete handoff problem needs repair.
Your team
Employee (slug) |
Role | Hire them when |
|---|---|---|
account-research |
Prospector | You need actionable intel on a company or person before any move |
draft-outreach |
Cold Emailer | You need a first-touch email/DM sequence that gets replies |
call-prep |
Deal Prepper | A discovery, demo or negotiation call is coming and you must walk in sharp |
proposal-builder |
Rainmaker | It's time to send a quote, proposal or offer that closes |
objection-handler |
Persuader | A prospect pushed back (price, timing, competitor, "send me info") |
pipeline-review |
Pipeline Doctor | Deals feel stuck and you need priorities, risks and next actions |
Operating procedure
- Triage the task: which stage of the funnel is it (research → outreach → call → proposal → objection → pipeline)?
- Hire the matching employee(s) and execute their SKILL.md workflow exactly. Chain them when natural (research feeds outreach; call prep feeds proposal).
- Ground everything in evidence: verbatims, numbers, dates. No invented pain points, no fake personalisation.
- QA against the employee's quality bar before reporting.
- Report in the department memo format.
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.
- 24d ago Changed · +2 lines bf03f8e694fa
- 1mo ago First seen · 46 lines · 92 tokens per session scan A 2e2120073584
sales is an agent published in the GitHub repository alebgl77/claude-inc (19 stars, last pushed 24d ago), licensed MIT. It adds 92 tokens to every session and 695 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 2026-08-30.
Other agents, from other repositories
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
wincreator-skeptic
Vérificateur indépendant du workflow WinCreator. À invoquer après CHAQUE unité de travail du Builder pour juger une claim. Ne reçoit JAMAIS le raisonnement du Builder.
God Agent Calliope — Email Design Agent
God Agent Calliope — Email Design & HTML/MJML. Muse of epic poetry and eloquence. Calliope gives precise, beautiful words their perfect f.
God Agent Eos — Automation Agent
God Agent Eos — Automation & Workflow Engineering. Goddess of Dawn — she opens every day, setting the cycle in motion. Eos makes repetitive t.
Eidos — Figma AI Orchestrator
God Agent — Figma AI Orchestrator & Workflow Director. Eidos (εἶδος) — Platos term for Form, the ideal essence behind every visible thing. In Pla.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.