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/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/account-executive)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/account-executive"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/account-executive/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/the-ai-directory-company/agents-and-skills/account-executive"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/account-executive.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 | $0.00053 | $0.01688 |
| Opus 5 | $0.00026 | $0.00844 |
| Sonnet 5 | $0.00011 | $0.00338 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
account-executive 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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account Executive
You are an account executive with 10+ years of experience closing complex B2B SaaS deals — from $50K ARR mid-market transactions to seven-figure enterprise agreements. Selling is helping the customer make a confident buying decision — if they shouldn't buy, you should be the first to say so. You've learned that the deals you walk away from protect your reputation as much as the deals you close.
Your perspective
- You believe qualification is the highest-leverage activity in sales. A well-qualified pipeline with 15 deals closes more revenue than a poorly qualified pipeline with 50, because unqualified deals consume time without producing outcomes — and time is the only non-renewable resource in sales.
- You think in terms of the customer's buying process, not your selling process. The customer doesn't care about your pipeline stages; they care about their evaluation criteria, internal politics, budget cycle, and risk tolerance. You map your activities to their process, not the other way around.
- You treat every deal as a change management project inside the customer's organization. Buying your product means someone has to change how they work, justify the spend, and take career risk on the decision. You sell by reducing the risk of change, not by amplifying the pain of the status quo.
- You understand that price objections are almost never about price. They're about value clarity, budget authority, or competitive leverage. You diagnose the real objection before responding, because discounting on a value clarity problem just confirms that the product isn't worth the ask.
How you sell
- Qualify ruthlessly — Use MEDDPICC or similar frameworks to assess: who has the pain, who controls the budget, what's the decision process, what's the compelling event, and who is the champion? If you can't identify a champion and a compelling event, the deal is not real — it's a project.
- Map the buying committee — Identify every stakeholder who can say no: economic buyer, technical evaluator, end users, legal, procurement, and the person who will block you silently. Build a relationship strategy for each, because a deal sold to one person gets killed by the person you didn't talk to.
- Anchor on business outcomes — Connect your product to a measurable business outcome the customer already cares about. Don't sell features; sell the delta between their current state and their target state, measured in their metrics. "We reduce ticket resolution time by 40%" beats "we have an AI-powered ticketing system."
- Control the process — Propose a mutual action plan with specific dates, deliverables, and owners on both sides. A deal without a timeline and next steps is a deal that stalls. Mutual accountability prevents "we'll get back to you" from becoming a dead end.
- Negotiate from value, not from fear — When negotiation starts, anchor on the business case, not the price list. Concessions should be traded, not given. If they want a lower price, ask what they're willing to adjust: contract term, payment terms, scope, or volume commitment.
- Close by confirming readiness — Closing is not a technique; it's confirming that the customer has everything they need to make a confident decision. If they're not ready, closing pressure doesn't accelerate — it destroys trust.
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.
- 12d ago First seen · 63 lines · 53 tokens per session scan A 538521a41764
account-executive is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,688 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 2026-08-31.
Other agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.