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/FounderOS --skill founderos-prompt-scaffoldgit clone --depth 1 https://github.com/impactbrussels/FounderOSWrote 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/founderos/founderos-prompt-scaffold)<a href="https://agentmods.dev/skills/impactbrussels/founderos/founderos-prompt-scaffold"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/founderos-prompt-scaffold/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/founderos/founderos-prompt-scaffold"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/founderos-prompt-scaffold.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 | $0.00097 | $0.01091 |
| Opus 5 | $0.00048 | $0.00545 |
| Sonnet 5 | $0.00019 | $0.00218 |
| Haiku 4.5 | $0.00010 | $0.00109 |
Grade A, and why
founderos-prompt-scaffold 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder OS Prompt Scaffold
This is the engine. Every Founder OS skill is this scaffold filled in for one founder job. Use it to author new skills, fix weak prompts, or teach a founder to get better output.
When to reach for this
- Authoring or editing any Founder OS skill → build the body against the scaffold.
- An AI answer came back generic, hedgy, or wrong-shaped → the prompt is under-specified; rebuild it with the right tier.
- A founder asks "how should I prompt for X" → hand them the matching tier.
The method
- Pick the lightest tier that does the job. Ceremony is a cost; founders are busy.
- Low - one-shot, you'll eyeball it:
role + task + format. - Medium - repeatable, defined output:
ROLE_AND_GOAL+STEPS+OUTPUT. - High - decision-grade (money, legal, hiring): all six blocks.
- Low - one-shot, you'll eyeball it:
- Fill every placeholder. Generic input → generic output. Use the shared glossary so vocabulary is consistent across skills (
[STARTUP_NAME],[STAGE],[ICP],[RISKIEST_ASSUMPTION],[CONSTRAINT], …). - Add
<CONSTRAINTS>naming the task's failure mode. Most bad output is a known trap (inventing facts, generic tone, skipping a step). Name it. - Define
<OUTPUT>precisely, and end with one concrete next action the founder can take. - For High tier, add
<QUALITY_STANDARDS>- 1-3 acceptance tests the founder can check themselves.
The full scaffold text, the six blocks, and the placeholder glossary live in
references/scaffold.md. The canonical copy is also at the repo's
templates/prompt-scaffold.md.
The four non-negotiable principles (enforced in every skill)
- Research before asserting - verify checkable claims or label them assumptions.
- A draft is not a decision - name what still needs a human call.
- Batch, then decide - generate, gather all feedback, revise once.
- Ask before assuming - one tight question beats the wrong artifact.
Output
- The chosen tier (Low / Medium / High) with a one-line reason it fits the task.
- The filled-in prompt - every placeholder resolved,
<CONSTRAINTS>naming the failure mode,<OUTPUT>precise - ending with one concrete next action.
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 · 78 lines · 97 tokens per session scan A 4c7ce4332416
founderos-prompt-scaffold is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,091 once invoked, about $0.0005 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
prompt-engineer
Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization.
prompt-lab
LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.
Prompt Engineering
Write better prompts for AI tools — structured, specific, and optimized for quality output.
prompt-engine
Ultimate AI prompt database and builder with 2,500+ curated prompts across 19 categories and 17 AI models (Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram, Adobe Firefly, and more). Search, build, enhance, and adapt prompts for image generation, video creation, text, and…
prompt-adapt
Adapt and convert AI prompts between different models and platforms. Translates between Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Stable Diffusion, Adobe Firefly, Ideogram, and more. Handles syntax differences, parameter mapping, and model-specific optimizations. Use when user says "adapt prompt", "convert…
prompt-enhance
Enhance and improve existing AI prompts using professional techniques from a 2,500+ prompt database. Adds detail, fixes structure, optimizes for specific models, and applies proven patterns from top-performing prompts. Use when user says "enhance my prompt", "improve this prompt", "make this prompt better", "optimize…