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 agentmods add skills/impactbrussels/ainativeos/start-herenpx skills add impactbrussels/AINativeOS --skill start-heregit clone --depth 1 https://github.com/impactbrussels/AINativeOSWhat 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 | $0.00133 | $0.01028 |
| Opus 5 | $0.00067 | $0.00514 |
| Sonnet 5 | $0.00027 | $0.00206 |
| Haiku 4.5 | $0.00013 | $0.00103 |
Grade A, and why
start-here 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Here
Founders rarely fail for lack of effort; they fail by pouring months into the wrong thing for the stage they're at. This skill's only job is to tell you where you are and the single next thing to do, then get out of the way. It also runs the one test that decides whether you're building a company or a feature.
The method
Diagnose the stage, run the Remove-the-AI test, route to one skill. Full build-arc map, the test in
full, the symptom-to-skill table, a worked diagnosis, and anti-patterns:
references/stage-diagnosis.md.
Step 1: Run the Remove-the-AI test
Ask: take the AI out of your product, does it still work? If yes, you have an AI feature, not an AI-native company. Before anything else, find the closed loop that would make it break without the intelligence. If there isn't one, that is the work.
Step 2: Locate the stage
Place the founder on the build arc by what they can't yet answer:
| If they can't answer… | They're at | Run next |
|---|---|---|
| "What's the sharp, falsifiable bet?" | Frame | frame-the-hypothesis |
| "Who's the market, and where's the regulatory/competitive wedge?" | Frame | map-the-terrain |
| "What's the system, before any code?" | Architect | architect-before-code |
| "How do I build it with agents without it collapsing?" | Build | agentic-build-loop |
| "How is this safe enough to act on a human?" | Trust | eval-and-safety-harness |
| "What's the smallest agent that proves the loop?" | Ship | design-the-mva |
| "Is it actually working?" | Grow | measure-ai-native-pmf |
Step 3: Route to the earliest unvalidated assumption
When two stages fit, send them upstream. The highest-value work is almost always the riskiest belief they haven't tested yet, not the most exciting one.
Output
- The result of the Remove-the-AI test, stated plainly (native or wrapper, and what's missing).
- The founder's current stage and the one skill to run next, with a one-line reason.
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.
- 2d ago First seen · 77 lines · 133 tokens per session scan A d7d6bcb6b30a
start-here is a skill published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,028 once invoked, about $0.0007 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
external-context
Invoke parallel document-specialist agents for external web searches and documentation lookup.
security-ownership-map
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
submit-github-pr
Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.
lemlist-campaign-from-icp
Use when the user says "create a lemlist campaign for X", "build a lemlist campaign from this ICP", "spin a lemlist campaign for Y", "ICP to lemlist", "natural language to lemlist campaign", "draft a lemlist campaign", "lemlist campaign for VPs/Managers/ICs at Z", or any variant indicating they want to turn a…
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.