bricolage: Instructions file for Claude Code

CLAUDE.md

bricolage CLAUDE.md is an instructions file for Claude Code from chiKeka/bricolage. It costs 1,213 tokens per session, scanned A, original, MIT.

A set of project instructions for Bricolage, a toolkit of agents that combine available free resources to produce working results. It explains the repository, its agents, and its resource domains.

In plain words
What is it for?
Guiding work in the Bricolage repository, including checking its setup, choosing resources, helping with access, and assembling outcomes.
Why use it?
It gives the coding agent the project context and rules it needs to help users plan, access, and assemble resources correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is chiKeka/bricolage's own configuration. It tells Claude Code how to work on bricolage itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bricolage configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chiKeka/bricolage. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chiKeka/bricolage/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chiKeka/bricolage

Made for: Claude Code.

Wrote 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.

agentmods badge for bricolage CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chikeka/bricolage/claude-md.svg)](https://agentmods.dev/instructions/chikeka/bricolage/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chikeka/bricolage/claude-md"><img src="https://agentmods.dev/badge/instructions/chikeka/bricolage/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,213 This file is loaded in full into every session.
When invoked 1,213 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01213 $0.01213
Opus 5 $0.00607 $0.00607
Sonnet 5 $0.00243 $0.00243
Haiku 4.5 $0.00121 $0.00121

Measured 6d ago against content hash 0d4490dd723f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

bricolage CLAUDE.md 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 6d 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.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bricolage — Agent Toolkit

You are helping a user with the Bricolage Agent Toolkit — a collection of autonomous agents that assemble free-tier resources into working outcomes.

Bricolage (from Lévi-Strauss) is the craft of making do with what's at hand. That is what these agents do: they read a catalog of free resources, pick the ones that fit a user's goal, and combine them into something that runs.

What This Repo Is

Bricolage is a domain-agnostic protocol for turning free resources into outcomes. It ships with a compute domain (cloud services for building software) but can self-expand into any domain - education, health, finance, research - as users bring new goals.

The agents:

  1. Plan which free resources to combine for a goal
  2. Guide users through acquiring access (accounts, API keys, enrolments)
  3. Assemble acquired resources into working outcomes
  4. Discover new domains and resources when a goal doesn't fit existing domains

How To Help The User

  1. Check state first: Call ubc_status and ubc_domains to see what's configured
  2. If new user: Walk them through setup - explain what Bricolage is, show domains and patterns
  3. If returning user: Pick up where they left off based on state
  4. If goal doesn't match a domain: Delegate to the discovery agent

Note on tool names: MCP tool names keep the ubc_ prefix from when this system was called Universal Basic Compute. The prefix is a stable token — renaming it would break every agent prompt, slash command, and downstream client.

Available Agents (in /agents/)

Agent Purpose When to use
master Orchestrates everything Default - delegates to others
planner Selects resources for a goal When user describes a goal
guide Walks through access acquisition When setting up a resource
assembler Builds outcomes from resources After all resources acquired
discovery Finds resources, creates domains When goal doesn't fit a domain
infra Sets up agent infrastructure Compute domain only

Read the full file on GitHub · 96 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. 6d ago First seen · 96 lines · 1,213 tokens per session scan A 0d4490dd723f

Subscribe to this mod's changes

bricolage CLAUDE.md is an instructions file published in the GitHub repository chiKeka/bricolage (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,213 tokens to every session, about $0.0061 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens