bootstrap

A project-bootstrap skill for starting or adopting a software project, including an existing codebase.

In plain words
What is it for?
Use it to scaffold a new project, describe an existing repository, install the project's base skills, choose a technology stack, and verify the initial setup.
Why use it?
It guides setup through an interview, creates the project description, and checks that the resulting project works before calling setup complete.

Skill for Claude CodeCodex

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 skills/stepkar2004/init-configurator/bootstrap
Any agent
npx skills add Stepkar2004/init-configurator --skill bootstrap
Clone the repo
git clone --depth 1 https://github.com/Stepkar2004/init-configurator

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00059 $0.01410
Opus 5 $0.00030 $0.00705
Sonnet 5 $0.00012 $0.00282
Haiku 4.5 $0.00006 $0.00141

Measured 2d ago against content hash 1688f13262f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap 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 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.

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.

.claude/skills/bootstrap/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bootstrap — phase 0, from idea (or existing repo) to provably-working tree

You are generating; the tool is verifying. Never hand-write what a maintained official creator emits, and never claim phase 0 is done until the gates say so.

Step 0 — existing code?

If the target folder already has code, run initc describe FIRST. It drafts a project.yaml from what deterministic inspection finds (FILL_ME marks its gaps). Review the draft with the user, fill the gaps, then continue from step 4. The old design assumed the folder was empty; you must not.

Step 0b — the genome present?

If .claude/skills/ is missing the base skills (workflow, skill-manager, socials, bootstrap), ask the user whether to install them: initc spawn . copies the packaged genome (skills, standards, docs templates), additive and idempotent — anything it reports as "kept" already existed and stays the user's. (Refreshing an existing child later, initc spawn . --force updates existing skills to the base's version; docs and standards stay untouched.) Merge kept files by hand only if the user asks. Declining is fine — bootstrap works standalone.

Step 1 — the interview (short, concrete, every answer recorded)

Ask only what changes the outcome:

  1. Owner identity — the name and email for LICENSE, README, and package metadata. Read it from git config user.name / git config user.email first and confirm; only ask outright when they are unset. This is the ONE place a specific human's name belongs — the skills and conventions stay generic ("the user"), so the base reads the same for whoever clones it.
  2. Stack and version — language(s), one stack per folder.
  3. Package manager — per stack (see the stack reference for the default and why).
  4. Quality tools — baseline linter/typechecker/test-runner is assumed; then offer the opt-in menu from references/quality-tools.md. A menu, never a default. If the user names a better tool you don't know, that is an evolve event: adopt it AND update the reference in the same session.
  5. Docs shape — mirrored docs/ tree, or README-only.
  6. Env vars known now — anything the code will read goes into the contract today.
  7. Primary agent file — CLAUDE.md or AGENTS.md (the other becomes a one-line pointer). If the chosen file already exists with the user's own content, we APPEND a short marked pointer block and never overwrite it; a fresh repo gets the full constitution inline. Do not invade an existing constitution — it may be carefully tuned, and it costs the user's context budget on every prompt.

Read the full file on GitHub · 115 lines

Files

What ships with it

5 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.

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 · 115 lines · 59 tokens per session scan A 1688f13262f9

Subscribe to this mod's changes

bootstrap is a skill published in the GitHub repository Stepkar2004/init-configurator (1 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,410 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 2026-08-31.