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 impactbrussels/AINativeOS --skill ai-assisted-salesgit clone --depth 1 https://github.com/impactbrussels/AINativeOSWrote 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/impactbrussels/ainativeos/ai-assisted-sales)<a href="https://agentmods.dev/skills/impactbrussels/ainativeos/ai-assisted-sales"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/ai-assisted-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/skills/impactbrussels/ainativeos/ai-assisted-sales"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/ai-assisted-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 | $0.00160 | $0.01553 |
| Opus 5 | $0.00080 | $0.00776 |
| Sonnet 5 | $0.00032 | $0.00311 |
| Haiku 4.5 | $0.00016 | $0.00155 |
Grade A, and why
ai-assisted-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 10d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Assisted Sales
Most of the work that loses you deals is not the selling. It is the connective tissue: reading the lead, pulling the case study, drafting the reply, logging it, setting the reminder. Hand that to a system that runs at three in the morning and your scarce humans show up only where judgement is required. But there is a deadlier trap. A demo books a pilot, the pilot earns a logo, the logo raises a round, and a signature got counted as revenue. A pilot is branded curiosity, not a contract. The core move: design every pilot with a written success bar and a path to paid before it starts.
The method
Map where money moves, automate the middleware, and gate every pilot to paid. Full framework: references/sales-motion.md, drawn from handbook Chapter 11.
Step 1: Map the path a dollar takes
Write the real sequence from first contact to signed and supported, the way it happens today. Mark each step with one word: where an agent helps, and where a human must stay.
| Stage | Agent role | Human gate |
|---|---|---|
| Qualify | read, score, route the lead | none |
| Scope | gather context, pull the case study, draft | the message that goes out |
| Pilot | run the agreed test, log signals | the success-bar call |
| Prove | compose the pilot report, run checks | verify before it ships |
| Expand | draft the renewal, surface usage | the close and the money |
Step 2: Draw the line and automate one step
Everything below the trust line runs as software; everything above it stays a person. Automate the single step that is most repetitive, most often where deals go cold, and lowest-risk to hand off. That one step is your first revenue agent, not the whole pipeline.
Step 3: Design the pilot with the bar set first
Before the pilot starts, write the success metric, the timebox, and the path to paid. No open-ended pilots. Use the pilot-design template in the reference.
| Pilot field | Set before start |
|---|---|
| Success metric | the one number that converts to a yes |
| Timebox | the date the pilot ends, fixed |
| Path to paid | the contract terms a pass triggers |
| Gate map | the procurement, security, compliance owners who must sign |
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.
- 10d ago First seen · 97 lines · 160 tokens per session scan A defd1d21d4ac
ai-assisted-sales is a skill published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 160 tokens to every session and 1,553 once invoked, about $0.0008 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 skills, from other repositories
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.
checkpoint
Create, list, or recover mid-workflow checkpoints so interrupted work resumes from a known-good position.