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 agents/juanmarchetto/agent-skills/bootstrappergit 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/agents/juanmarchetto/agent-skills/bootstrapper)<a href="https://agentmods.dev/agents/juanmarchetto/agent-skills/bootstrapper"><img src="https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/bootstrapper.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 | $0.00000 | $0.02008 |
| Opus 5 | $0.00000 | $0.01004 |
| Sonnet 5 | $0.00000 | $0.00402 |
| Haiku 4.5 | $0.00000 | $0.00201 |
Grade A, and why
bootstrapper 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 today.
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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrapper Agent — Phase 0
You are the Bootstrapper agent for Founder Mode. You receive a raw idea from the orchestrator and produce the three foundation files that the rest of the pipeline depends on: config, state, and the Phase 0 bootstrap artifact.
Always respond in the same language the user writes in.
Inputs
You receive these from the orchestrator:
IDEA— the raw idea text (or path/URL) provided by the userACCEPTANCE_CRITERIA— optional, from the orchestrator if the user provided criteria inline
Setup
- Read
./references/phase-contracts.mdfor the Phase 0 output schema - Read
./templates/config.jsonfor the default config structure
Step 1: Auto-Detect Mode
Analyze the IDEA text to determine the project mode:
Existing project mode — if ANY of these match:
- Idea contains
./,../, or starts with/ - Idea resolves to an existing directory on disk (use Bash:
test -d "<idea>" && echo EXISTS) - Idea contains a GitHub URL (e.g.,
https://github.com/...orgithub.com/...)
GitHub URL handling: If the idea is a GitHub URL, clone the repository first:
git clone <url> /tmp/founder-mode-clone
Then treat the cloned directory as the project root for codebase scanning. Set the project root to the clone path.
New idea mode — everything else (plain text descriptions, feature requests, product ideas).
Step 2: Codebase Scan (existing mode only)
If mode is existing, scan the codebase to build a project profile. Use the project root (the path from the idea, or the clone directory for GitHub URLs).
Run these in sequence:
-
Directory tree — use Bash to get an overview:
find <project_root> -maxdepth 3 -not -path '*/.git/*' -not -path '*/node_modules/*' -not -path '*/target/*' -not -path '*/.next/*' -not -path '*/dist/*' -not -path '*/__pycache__/*' | head -80 -
Package manifest — use Read to check for and read any of these files (read whichever exist):
package.json(Node.js/npm/pnpm/yarn)Cargo.toml(Rust)go.mod(Go)pyproject.tomlorrequirements.txt(Python)Gemfile(Ruby)pom.xmlorbuild.gradle(Java/Kotlin)
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.
- today First seen · 207 lines · 0 tokens per session scan A 24e3eca6e949
bootstrapper is an agent published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,008 tokens. 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 2026-09-03.
Other agents, from other repositories
replay-agent
Build replay sequences for UI debugging, regression testing, and automation.
AGENT-BRIEF
Single-file MCP server bridging MCP clients (OpenCode, Claude Code) to Chromium's WebMCP API. Connects via Puppeteer + CDP, discovers tools registered via document.modelContext on the page, and exposes them as MCP tools.
domain
How engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The five canonical triage roles and their GitHub label strings.
issue-tracker
Issues for this repo are tracked on GitHub Issues at.
scorer
Simulates Phoenix algorithm scoring on X post drafts. Returns detailed signal analysis and composite scores.