bootstrap

A command for preparing a repository for Claude Code by creating or reconciling project guidance and settings. It first identifies whether the repository is new, unmanaged, legacy, or already configured.

In plain words
What is it for?
Use it when setting up Claude Code in a new or existing repository, or when the project's structure and conventions have changed. It can create guidance and settings in the appropriate owner or contributor locations.
Why use it?
Coding agents need accurate project instructions, but older or missing CLAUDE.md files can lead to inconsistent work. This maps the repository and proposes the needed guidance, safeguards, and tool connections.

Command

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/ohswedd/praxis/bootstrap
Clone the repo
git clone --depth 1 https://github.com/Ohswedd/praxis
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 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 $0.00021 $0.00316
Opus 5 $0.00010 $0.00158
Sonnet 5 $0.00004 $0.00063
Haiku 4.5 $0.00002 $0.00032

Measured yesterday against content hash 2893aa6762b6, 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 yesterday.

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.

plugins/praxis/commands/bootstrap.md · 28 lines

What it actually says

Use the bootstrap skill to set up this repository for Claude Code.

This normally runs on its own: any session that does real work in a repo praxis has not set up bootstraps it first, in the same turn. Running the command is the same setup asked for explicitly, and it is also how you re-run it after the repo has moved on.

Classify the repo state (new / uninitialised / legacy / managed), then follow the skill: map the codebase read-only, generate or reconcile the brief hierarchy (route any legacy file through @praxis:claudemd-verifier), propose the settings guardrails, and propose LSP/MCP wiring via capability-discovery.

Check the workspace mode first (config.py status, or the session audit). In owner mode praxis writes the project's own committed files. In contributor mode the repository is not ours: the brief is CLAUDE.local.md, settings are .claude/settings.local.json, knowledge lands under .claude/.praxis/knowledge/, all git-excluded, and the repo itself gets nothing.

Write what does not exist; show the diff and confirm before reconciling anything praxis did not author.

Target: ${ARGUMENTS:-the current project directory}.

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. yesterday First seen · 28 lines · 21 tokens per session scan A 2893aa6762b6

Subscribe to this mod's changes

bootstrap is a command published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 316 once invoked, about $0.0001 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.