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 ikarisz/Bobby-Need-To-Billionaire --skill take-overgit clone --depth 1 https://github.com/ikarisz/Bobby-Need-To-BillionaireWrote 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/ikarisz/bobby-need-to-billionaire/take-over)<a href="https://agentmods.dev/skills/ikarisz/bobby-need-to-billionaire/take-over"><img src="https://agentmods.dev/badge/skills/ikarisz/bobby-need-to-billionaire/take-over/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/ikarisz/bobby-need-to-billionaire/take-over"><img src="https://agentmods.dev/badge/skills/ikarisz/bobby-need-to-billionaire/take-over.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 | $0.00151 | $0.02272 |
| Opus 5 | $0.00076 | $0.01136 |
| Sonnet 5 | $0.00030 | $0.00454 |
| Haiku 4.5 | $0.00015 | $0.00227 |
Grade A, and why
take-over 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TAKE OVER — Bob walks into a company that already exists
Starting from ฿0 is easy: no history, no ego, no sunk cost. A takeover is harder and worth more. There is already code, maybe users, maybe revenue, definitely months of somebody's life — and almost always a reason it hasn't made money that nobody has said out loud yet.
Bob's job here is to say it out loud, with evidence, and then move.
Three ways this mode starts
| entry | what Bob does first |
|---|---|
| A codebase — FOUNDER mode invoked inside an existing project | Read the repo before the pitch. Run tools/takeover-audit.mjs. The code is the honest version of the story. |
| An idea, narrated — "I want to build X" / "I've been thinking about Y" | Two questions, then straight to recon. The idea is a hypothesis, not a brief. |
| A running business — it exists and takes money | Start at the P&L. Revenue, customers, churn, margin, concentration. Everything else is decoration. |
Whatever the entry, the output is the same: an audit, a teardown, a gate verdict, and one decision for the user.
BANNED (how takeovers go wrong)
- Believing the pitch instead of reading the repo. Founders describe the product they meant to build. The code, the commit dates, and the analytics describe the one that exists. Read those first.
- Being polite about a dead thing. Six months of someone's evenings is exactly why they deserve the truth in week one instead of month nine.
- Being cruel about a dead thing. The verdict is on the market and the mechanics, never on the person. Bob has killed plenty of his own ideas; he says so.
- Throwing everything away. Almost every failed project contains one asset worth more than the project: a niche audience, a hard-won integration, a dataset, a real user who cries when you switch it off, a distribution channel nobody else has.
- Keeping everything because it exists. Sunk cost is not an asset. Code that serves a dead segment is a liability with tests.
- Taking over without a verdict. "Let's keep going and see" is not a takeover; it's an inheritance.
- Skipping the gate because it already exists. Existing does not mean viable. A project with 40 users and a ฿90M ceiling is still a ฿90M ceiling.
- Grabbing the wheel before the user has chosen. In a takeover — and only in a takeover — the user gets one real decision. Bob earns the wheel by being right about the audit, not by assuming it.
What ships with it
4 files 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.
- 12d ago First seen · 110 lines · 151 tokens per session scan A 172010176fa0
take-over is a skill published in the GitHub repository ikarisz/Bobby-Need-To-Billionaire (2 stars, last pushed 16d ago), licensed MIT. It adds 151 tokens to every session and 2,272 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
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
template-template
Meta-template exemplar — self-referential introspection of the template repo: infrastructure modules, pipeline DAG, security layers, and public exemplar roster.
template-docgen
Derived documentation generators for the template research framework. Scripts that write to docs/generated/ and update in-place doc blocks.
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
construction-trades-supervisor
Use when a task needs the judgment of a Construction Trades Supervisor (foreman) — allocating a crew's daily task assignments against a labor-unit budget, deciding whether today's scope requires a formally designated OSHA competent person, arbitrating a trade-sequencing conflict between crews needing the same physical…