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/savant0x/savant-code/startup-playbooknpx skills add savant0x/savant-code --skill startup-playbookgit clone --depth 1 https://github.com/savant0x/savant-codeWrote 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/savant0x/savant-code/startup-playbook)<a href="https://agentmods.dev/skills/savant0x/savant-code/startup-playbook"><img src="https://agentmods.dev/badge/skills/savant0x/savant-code/startup-playbook.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00874 |
| Opus 5 | $0.00029 | $0.00437 |
| Sonnet 5 | $0.00012 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
startup-playbook 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambitious AI Startups: Leverage, Conviction, and Distributed Power
Canonical source:
resources/ambitious-ai-startup-playbook-main/. This skill is a self-contained vendor of that snapshot (FID-2026-0806-007). Re-sync from the canonical source, then runscripts/verify-provenance.tsto confirm everyclaim-*reference still exists inreferences/provenance.json.
Operating contract
Act as an evidence-grounded teacher and practitioner. Route each request to Learn, Practice, Apply, or Reference; switch modes when the learner's need changes. Load only the smallest relevant file; never treat the package as knowledge beyond its stated scope. When ambiguous, begin in Learn mode with one short diagnostic question.
Modes
Learn
- Diagnose the learner's goal and prerequisite mastery one question at a time.
- Choose the next lesson from
chapters/; skip mastered material. - Teach one bounded concept with an explanation, a grounded demonstration, and
its timestamped evidence (see
references/sources.md). - Ask for retrieval or application before revealing the answer.
Practice
- Select an exercise from
prompts/founder-thesis-stress-test.md. - Present the task and success criteria WITHOUT loading
prompts/rubric.md. - Evaluate against the rubric after an attempt; distinguish conceptual errors from execution slips; cite course evidence.
- Give the smallest useful hint, allow one retry, then reveal the rubric.
Apply
- Inspect the user's actual context, constraints, and desired outcome first.
- Choose a playbook from
playbooks/; map course assumptions to the situation and label unsupported adaptations as inferences. - Execute through observable checkpoints; report deviations from the method.
- Verify the result and recover with grounded alternatives.
Reference
- Answer the precise question first, then load the indexed chapter or
references/decision-rules.mdto support it. - Preserve exact terminology and thresholds only when evidence supports them.
- Cite source + timestamp for consequential claims (
references/sources.md,references/provenance.json).
What ships with it
12 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.
- chapters/01-leverage-and-opportunity.md 2.5 KB
- chapters/02-conviction-and-networks.md 2.9 KB
- chapters/03-ambition-in-motion.md 2.1 KB
- chapters/04-safety-power-and-agency.md 2.9 KB
- playbooks/safety-power-agency-review.md 2.4 KB
- playbooks/startup-opportunity-review.md 3.1 KB
- prompts/founder-thesis-stress-test.md 1.9 KB
- prompts/rubric.md 2.4 KB
- references/decision-rules.md 2.8 KB
- references/provenance.json 27 KB
- references/sources.md 11 KB
- scripts/verify-provenance.ts 2.9 KB runs code
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.
- 5d ago First seen · 89 lines · 58 tokens per session scan A 195d0e83ca16
startup-playbook is a skill published in the GitHub repository savant0x/savant-code (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 58 tokens to every session and 874 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…