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 JuanMarchetto/agent-skills --skill founder-modegit clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote 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/juanmarchetto/agent-skills/founder-mode)<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/founder-mode"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/founder-mode/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/juanmarchetto/agent-skills/founder-mode"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/founder-mode.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 | $0.00096 | $0.01229 |
| Opus 5.5 | $0.00038 | $0.00492 |
| Sonnet 5.5 | $0.00019 | $0.00246 |
| Haiku 4.5 | $0.00010 | $0.00123 |
Grade A, and why
founder-mode 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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder Mode — End-to-End Product Builder
From idea to launched product. Not just code — a product.
How It Works
/founder-mode "Build a CLI that converts markdown to slides"
│
▼
Phase 0: Bootstrap ─── config.json + state.json + mode detection
│
▼
Phase 1: Idea Evaluation ─── /architect dispatches 6 evaluators
│
▼
══ GATE 1 ══ Go/No-Go decision ─── [continue|reject|iterate|edit]
│
▼
Phase 2: Architecture ─── system design, components, tech stack
│
▼
Phase 3: TDD Planning ─── decompose into test-first chunks
│
▼
Phase 4: Implementation ─── chunk-with-summary TDD loop
│
▼
══ GATE 2 ══ Implementation review ─── [continue|iterate|stop|edit]
│
▼
Phase 5: E2E Testing ─── strategy by project type
│
▼
Phase 6: Verification ─── false positives + spec-to-test gap + arch drift
│
▼
══ GATE 3 ══ Verification review ─── [continue|iterate|stop|edit]
│
▼
Phase 7: Post-Run Analysis ─── lessons + recommendations
│
▼
Phase 8: GTM Draft ─── README + pitch + tweets + PH + CHANGELOG
│
▼
DONE ─── all artifacts in .founder/
Phases
| Phase | What It Does | Agent |
|---|---|---|
| 0 - Bootstrap | Config generation, mode detection, codebase scan (existing projects), lesson loading | bootstrapper.md |
| 1 - Evaluation | Dispatches 6 parallel evaluators via /architect, extracts acceptance criteria |
evaluator.md |
| 2 - Architecture | Generates system design (new) or reverse-engineers from codebase (existing) | architect-gen.md |
| 3 - TDD Planning | Decomposes architecture into ordered test-first chunks | planner.md |
| 4 - Implementation | TDD per chunk with cross-chunk summaries, supports re-entry for fixes | implementer.md |
| 5 - E2E Testing | Generates and runs E2E tests matched to acceptance criteria | e2e-runner.md |
| 6 - Verification | False-positive detection, spec-to-test gap analysis, architecture drift check | verifier.md |
| 7 - Analysis | Post-run pattern analysis, lesson extraction, recommendations | analyzer.md |
| 8 - GTM Draft | README, pitch, tweet thread, Product Hunt listing, CHANGELOG | gtm-drafter.md |
What ships with it
20 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.
- .claude-plugin/plugin.json 364 B
- .gitignore 26 B
- agents/analyzer.md 10 KB
- agents/architect-gen.md 7.4 KB
- agents/bootstrapper.md 7.5 KB
- agents/e2e-runner.md 9.9 KB
- agents/evaluator.md 5.4 KB
- agents/gtm-drafter.md 12 KB
- agents/implementer.md 9.8 KB
- agents/planner.md 4.9 KB
- agents/verifier.md 8.6 KB
- commands/founder-mode.md 13 KB
- README.md 2.9 KB
- references/phase-contracts.md 8.9 KB
- templates/changelog-template.md 394 B
- templates/config.json 649 B
- templates/pitch-template.md 502 B
- templates/producthunt-template.md 489 B
- templates/readme-template.md 630 B
- templates/tweet-thread-template.md 617 B
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.
- 1mo ago First seen · 120 lines · 96 tokens per session scan A f21517e8a976
founder-mode is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 96 tokens to every session and 1,229 once invoked, about $0.0004 per session on Opus 5.5. 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
testing
TDD/BDD testing principles. Use when writing tests, reviewing test coverage, setting up testing, or discussing test strategy and test architecture.
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.
qa-runner
Use when asked to "run QA", "qa check", "test checklist", or execute QA checklists against a running app via browser automation. Requires the browser-bridge MCP server and Chrome extension.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
BrowserBash Browser Automation
BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream NDJSON results with CI exit codes — using free local Ollama…