context-foundry CLAUDE.md

Project instructions for Context Foundry, a system that captures reusable solutions so AI agents can improve across projects. They cover building, installing, local-model setup, and the packaging of skills and plugins.

In plain words
What is it for?
Rebuilding and installing the tool, testing local-model routing, maintaining skills and plugins, and verifying changes with the project's smoke tests.
Why use it?
They prevent contributors from using stale builds or outdated knowledge files and define the checks needed after changes.

Instructions file

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 instructions/context-foundry/context-foundry/claude-md
Clone the repo
git clone --depth 1 https://github.com/context-foundry/context-foundry
Per session 2,577 This file is loaded in full into every session.
When invoked 2,577 The same file — it is already loaded in full.
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 $0.02577 $0.02577
Opus 5 $0.01288 $0.01288
Sonnet 5 $0.00515 $0.00515
Haiku 4.5 $0.00258 $0.00258

Measured 2d ago against content hash fd9fee9a986e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-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 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.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Foundry

Context Foundry is a pattern-learning system that helps AI agents improve over time by capturing and sharing solutions to common problems.

Build & Install

After any code change, rebuild and install:

cd ~/homelab/context-foundry && cargo build --release && cp target/release/foundry ~/.cargo/bin/ && codesign -s - --force ~/.cargo/bin/foundry

Run from any project directory:

cd ~/some-project && foundry

IMPORTANT: The running TUI does NOT hot-reload. You must quit the TUI, rebuild, and restart to pick up changes. If you see errors like No such tool available: Write, you are running a stale binary.

Local Models

LM Studio + opencode is wired into the builder pipeline via Phase 32. Runbook: docs/local-model-setup.md. Smoke gate: bash scripts/smoke-local-model.sh (asserts schema_version, opencode routing, and typed-error absence).

Skills and Plugins

Domain knowledge lives in skills (Anthropic SKILL.md format) packaged inside plugins. Skills replaced the legacy ~/.foundry/patterns/ JSON store; the pattern catalog is still emitted in dual-emit mode for back-compat but new knowledge should be written as a SKILL.md under the relevant plugin.

  • On-disk layout: plugins/<plugin>/skills/<slug>/SKILL.md
  • Global skills: ~/.foundry/skills/
  • Global plugins: ~/.foundry/plugins/

Before starting a task, read the matching plugin's CLAUDE.md and any SKILL.md files whose frontmatter matches the task domain.

Plugins

Context Foundry has domain-specific plugins (formerly called "extensions"). When working on tasks for a specific domain, read that plugin's CLAUDE.md first. The on-disk directory is plugins/. The legacy extensions/ name is auto-migrated on first startup; do not reference it in new code or docs.

Roblox Plugin

Location: plugins/roblox/ When to read: Any Roblox world generation, Lune scripting, or .rbxl/.rbxm work

IMPORTANT - Read before Roblox work:

  • plugins/roblox/CLAUDE.md - Critical patterns and commands
  • plugins/roblox/skills/roblox-common-pitfalls/SKILL.md - Learned pitfalls (Anthropic Skills format)

Read the full file on GitHub · 227 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 · 227 lines · 2,577 tokens per session scan A fd9fee9a986e

Subscribe to this mod's changes

context-foundry CLAUDE.md is an instructions file published in the GitHub repository context-foundry/context-foundry (19 stars, last pushed 2mo ago), licensed MIT. It adds 2,577 tokens to every session, about $0.0129 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 2026-08-30.

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

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

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

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 · 4,345 tokens