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.
npx agentmods add instructions/ai-supervisor-foundry/foundry/claude-mdgit clone --depth 1 https://github.com/ai-supervisor-foundry/foundryWrote 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.
[](https://agentmods.dev/instructions/ai-supervisor-foundry/foundry/claude-md)<a href="https://agentmods.dev/instructions/ai-supervisor-foundry/foundry/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-supervisor-foundry/foundry/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- foundry GEMINI.md — 86% identical, 8 lines differ
What it actually says
Foundry — Agent Instructions
Read supervisor-contexts/CONTEXT.md first — it indexes all system documentation.
For each *.md or context file, first read the frontmatter (Lines between "---" in the starting of the file) by doing a head -5 before proceeding - if not required, skip file.
Always-Apply Behavioral Rules
- Be concise unless asked for elaboration.
- Propose = suggest without edits.
- After root cause/fix identified, NEVER run commands—verify I approve.
- Check MCP availability before asking.
- Questions → answer only, no mutating actions.
- Mistake → alert, inform, halt. No changes.
Cursor Rules (.cursor/rules/)
- always: Concise responses, propose-only, 6-line limit, verify approval, questions=answer-only, halt on mistakes
- supervisor-specs: Operator goals only, no scope expansion, deterministic validation, no anti-goals
- task-lifecycle: Blocked tasks never autocompleted — set to pending for supervisor
- cleanup: Ask before cleanup/delete; use ./tmp for *.baks
- pm2: Logs always
--nostream; lifecycle: halt→stop→rebuild→restart→resume - secrets: Never print secrets; shell-based length check only
- mcp: Tool fail → report and halt
- restart: Halt→stop→rebuild→restart→resume
- contexts: Read CONTEXT.md first; use supervisor-contexts/ for system, contexts/ for projects
Conditional Contexts
- System docs:
supervisor-contexts/(read specific section files as needed) - Project details:
README.md,docs/*.md(notdocs/plansunless working on a plan) - Sandbox projects:
contexts/sandbox/ - UI Dashboard:
UI/— Express API backend + React frontend; entry point:UI/CLAUDE.md - Core source:
src/— seesrc/CLAUDE.md - Tests:
tests/— seetests/CLAUDE.md - Scripts:
scripts/— seescripts/CLAUDE.md
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.
- yesterday First seen · 41 lines · 563 tokens per session scan A 65ec7db38643
foundry CLAUDE.md is an instructions file published in the GitHub repository ai-supervisor-foundry/foundry (11 stars, last pushed 1mo ago), licensed MIT. It adds 563 tokens to every session, about $0.0028 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 2026-09-02.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.