What is foundry CLAUDE.md?

Project instructions for Foundry, a system that coordinates several AI agents to work through Linear tickets, which are tasks tracked in the Linear project-management tool.

Use them when building, running, configuring, or changing Foundry, including its Claude and Codex agent processes.

They give coding agents the project’s build commands, architecture, directory layout, configuration, and agent workflow in one place.

How leixusam/foundry configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to leixusam/foundry. 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/leixusam/foundry/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/leixusam/foundry

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/leixusam/foundry/claude-md/github.svg)](https://agentmods.dev/instructions/leixusam/foundry/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/leixusam/foundry/claude-md"><img src="https://agentmods.dev/badge/instructions/leixusam/foundry/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/leixusam/foundry/claude-md"><img src="https://agentmods.dev/badge/instructions/leixusam/foundry/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 669 This file is loaded in full into every session.

When invoked 669 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.

Model	Per session	Once invoked
Fable 5.1	$0.00669	$0.00669
Opus 5.5	$0.00268	$0.00268
Sonnet 5.5	$0.00134	$0.00134
Haiku 4.5	$0.00067	$0.00067

Measured 2mo ago against content hash 9110ad9e04af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

foundry 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 2mo 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foundry - Autonomous Product Development System

This is the core Foundry autonomous development loop. Foundry orchestrates multiple AI agents to work on Linear tickets autonomously.

Build & Run

Install: npm install
Build: npm run build
Start: npm run start
Dev: npm run dev (watch mode)
Typecheck: npm run typecheck

Architecture

Agent Pipeline

Agent 1 (Linear Reader): Scans Linear for tickets, claims work
Agent 2 (Worker): Executes the actual development work
Agent 3 (Linear Writer): Updates Linear with results

Directory Structure

src/ - TypeScript source code
dist/ - Compiled JavaScript (gitignored)
prompts/ - Agent prompt templates

Key Files

src/index.ts - Main loop entry point
src/config.ts - Configuration management
src/lib/claude.ts - Claude Code spawner
src/lib/codex.ts - Codex CLI spawner
src/lib/prompts.ts - Prompt loader

Environment Variables

FOUNDRY_PROVIDER - "claude" (default) or "codex"
FOUNDRY_CLAUDE_MODEL - "opus" (default), "sonnet", or "haiku"
FOUNDRY_MAX_ITERATIONS - Limit iterations (0 = unlimited)
CODEX_MODEL - Codex model name
CODEX_REASONING_EFFORT - "low", "medium", "high" (default), "extra_high"

Output

Runtime logs are written to .foundry/output/ (gitignored). Output folder names are prefixed with timestamps for easy sorting (e.g., 20250126-051600-swift-wyvern/).

Project Artifacts

The foundry-docs/ directory at project root stores Foundry's work artifacts:

foundry-docs/research/ - Research documents for tickets
foundry-docs/plans/ - Implementation plans
foundry-docs/validation/ - Validation reports
foundry-docs/shared/ - Shared context between sessions

Releasing (Maintainers)

Releases are performed via GitHub Actions (see README.md for the full checklist).

GitHub → Actions → Release (branch: main)
- Inputs: release_type (patch|minor|major), npm_tag (default latest), dry_run (true runs CI only)
- Requires NPM_TOKEN secret; optionally RELEASE_TOKEN if the workflow needs to push to a protected main and/or create the GitHub Release.
Recovery: If a tag exists but publish failed, run Publish existing ref to npm with ref = vX.Y.Z.
- Note: Publish existing ref to npm is a manual recovery workflow (workflow_dispatch); it does not run automatically on GitHub Release events.

Read the full file on GitHub · 63 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.

2mo ago First seen · 63 lines · 669 tokens per session scan A 9110ad9e04af

Subscribe to this mod's changes

foundry CLAUDE.md is an instructions file published in the GitHub repository leixusam/foundry (11 stars, last pushed 8mo ago), licensed MIT. It adds 669 tokens to every session, about $0.0027 per session on Opus 5.5. 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 2026-08-30.

Building agents Project management

foundry CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
foundry CLAUDE.mdleixusam/foundry	Instructions file	11	8mo ago	MIT	A	669	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

foundry: Instructions file for Claude Code