bootstrap

A setup wizard for analyzing a project, interviewing the developer, and creating an agent-based workflow configuration. It prepares folders, instruction files, a manifest, and a backlog.

In plain words
What is it for?
It helps bootstrap a project with agent configuration, root guidance files, workflow rules, and an initial list of work.
Why use it?
It removes the need to design the initial agent setup and project workflow structure by hand.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/varienos/agentic-workflow/bootstrap
Clone the repo
git clone --depth 1 https://github.com/varienos/agentic-workflow

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 43,414 The whole file, excluding the scripts and references it only reads on demand.
Security scan E 4 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.43414
Opus 5 $0.00000 $0.21707
Sonnet 5 $0.00000 $0.08683
Haiku 4.5 $0.00000 $0.04341

Measured 2d ago against content hash 4ae90e1d48ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

bootstrap scanned grade E with 4 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

test -f ./.claude/settings.json && echo "✅ C1: settings.json var" || echo "❌ C1: settings.json YOK"

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

grep -q '"basic-memory"' ./.mcp.json && echo "✅ I2: .mcp.json basic-memory entry içeriyor" || echo "❌ I2: .mcp.json basic-memory entry EKSIK"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LsSf https://astral.sh/uv/install.sh | sh
Agentbase/.claude/commands/bootstrap.md · 2,952 lines

How it starts

The opening of the file, as written. The whole thing — 2,952 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap — Agentic Workflow Kurulum Sihirbazi

Bu komut projenizi analiz eder, sizinle kisa bir roportaj yapar ve tum agentic workflow yapilandirmasini olusturur. Her adim konsolda gorunur. Islem sonunda .claude/ dizini, root dosyalar, manifest ve backlog hazir olur.

KURAL: Bu talimatlari harfi harfine, ADIM ADIM, sirasiyla uygula. Hicbir adimi atlama, hicbir adimi birlestirme. Her adimdaki ciktilari kullaniciya goster.

KUTSAL KURALLAR

Bu kurallar Bootstrap'in ve urettigi tum dosyalarin temelini olusturur:

1. Git sadece Codebase'de calisir

  • Agentbase'de .git/ YOKTUR. Agentbase sadece bir konfigürasyon dizinidir.
  • Tum git islemleri (commit, push, branch, worktree) ../Codebase/ icinde yapilir.
  • Command'lardaki git komutlari: cd ../Codebase && git ...
  • Worktree izolasyonu: cd ../Codebase && git worktree add ...
  • Bu ayrim Codebase'in guvenli worktree izolasyonunu saglar — agent ve backlog dosyalarindan bagimsiz.
  • Iki-repo teslimat modeli (opsiyonel): Proje koku (Agentbase/Codebase/Docbase'in USTU) gelistiricinin KENDI git reposu olabilir — Agentbase + Docbase'i versiyonlar, Codebase'i .gitignore ile yok sayar (bkz. ADIM 6.6). Codebase kendi bagimsiz reposudur ve musteriye AYRI teslim edilir (musteri sadece Codebase'i klonlar). Bu durumda bile .git proje kokune yazilir; Agentbase icine YAZILMAZ — yukaridaki "Agentbase'de .git/ YOKTUR" kurali aynen korunur.
  • Ajan siniri: Ajan/workflow git islemleri (commit/push/branch/worktree) DAIMA ../Codebase/'i hedefler; ust-kok (gelistirici) reposuna ASLA dokunmaz. Ust-kok repo gelistiricinin manuel aracidir, ajanlarin degil.

2. Bootstrap Codebase'e ASLA yazmaz (tek istisna: AI Import)

  • Bootstrap Codebase'i OKUR → Agentbase'i YAPILANDIRIR.
  • Codebase'deki hiçbir dosya degistirilmez, eklenmez veya silinmez.
  • Tum uretilen dosyalar Agentbase/ icine gider — alt dagilim:
    • Agentbase ROOT (yani Agentbase/ direkt) — Bootstrap'in DOĞRUDAN urettigi (6+1 root dokuman + 1 mcp config): PROJECT.md, STACK.md, DEVELOPER.md, ARCHITECTURE.md, WORKFLOWS.md, CLAUDE.md (root context), onboarding.md (yeni gelistirici rehberi), .claude-ignore, .mcp.json (zorunlu — templates/core/mcp.skeleton.json kaynagindan). Bootstrap'in cagirdigi araclarin urettigi: backlog/ (Backlog.md CLI), ../Docbase/memory/ (basic-memory vault). Repo'da hazir gelen (statik root dokumanlar — Bootstrap doldurmaz, root CLAUDE.md'deki @<dosya> zincirine dahil edilir): ORCHESTRATION.md (ortak ajan davranis felsefesi — tum modeller icin), LESSONS.md (oz-gelisim dersleri), BACKLOG.md (Backlog CLI hizli referans). Repo'da hazir gelen (kod ve template altyapisi): bin/, templates/, tests/, generate.js, transform.js, package.json.
    • Agentbase/.claude/ altinda: commands/, agents/, hooks/, rules/, reports/, tracking/, custom/, settings.json, CLAUDE.md (agent-icin dahili runtime config — root CLAUDE.md'den AYRI bir dosya, son kullaniciya degil agent'a yoneliktir).
    • Manifest: ../Docbase/agentic/project-manifest.yaml (Agentbase disinda, Docbase altinda).
    • Transform.js opsiyonel ciktilari (manifest.targets icinde claude disinda hedef varsa): GEMINI.md (gemini/antigravity hedefi → Agentbase root), .agents/workflows/*, .agents/skills/*/SKILL.md, .agents/rules/* (antigravity hedefi), AGENTS.md + .codex/skills/*/SKILL.md (codex hedefi → Agentbase root + .codex/), .kimi/skills/, .kimi/agents/ (kimi hedefi), .opencode/AGENTS.md + .opencode/skills/ + .opencode/agents/ (opencode hedefi). Bu dosyalar root CLAUDE.md icerigini hedef CLI formatina cevirir — enjeksiyon zinciri otomatik korunur.
    • YASAK: Root dokumanlari (PROJECT.md, STACK.md, DEVELOPER.md, ARCHITECTURE.md, WORKFLOWS.md, ORCHESTRATION.md, LESSONS.md, BACKLOG.md, root CLAUDE.md, onboarding.md) .claude/ altina YAZMA veya KOPYALAMA. .claude/ agent runtime konfiguudur, dokumantasyon degil. Bu dosyalar gercek Agentbase root'unda kalir ki tum modeller (Claude, Gemini, Antigravity, Codex, Kimi, OpenCode) ayni context'i okuyabilsin.
  • Manifest ../Docbase/agentic/ altina gider (Codebase disinda).
  • Projenin mevcut .gitignore, package.json, CI config dosyalari korunur.

Read the full file on GitHub · 2,952 lines

Changes

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.

  1. 2d ago First seen · 2,952 lines · 0 tokens per session scan E 4ae90e1d48ac

Subscribe to this mod's changes

bootstrap is a command published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 43,414 tokens. A static security scan graded it E with 4 findings (downloads and executes remote code, reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.