foundry SANDBOX.instructions.md

foundry SANDBOX.instructions.md is an instructions file for GitHub Copilot from ai-supervisor-foundry/foundry. It costs 351 tokens per session, scanned B, original, MIT.

Instructions for ai-supervisor-foundry/foundry, covering always-apply behavioral rules, cleanup rules, mcp rules, secrets rules and project context.

Instructions file for GitHub Copilot

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/ai-supervisor-foundry/foundry/sandbox
Clone the repo
git clone --depth 1 https://github.com/ai-supervisor-foundry/foundry

Made for: GitHub Copilot.

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 foundry SANDBOX.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ai-supervisor-foundry/foundry/sandbox.svg)](https://agentmods.dev/instructions/ai-supervisor-foundry/foundry/sandbox)
Your own site
<a href="https://agentmods.dev/instructions/ai-supervisor-foundry/foundry/sandbox"><img src="https://agentmods.dev/badge/instructions/ai-supervisor-foundry/foundry/sandbox.svg" alt="Measured on agentmods" height="20"></a>
Per session 351 This file is loaded in full into every session.
When invoked 351 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00351 $0.00351
Opus 5 $0.00176 $0.00176
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured yesterday against content hash 15db6052b00b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

foundry SANDBOX.instructions.md scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

4. After root cause found or fix identified or suspected, NEVER run any commands, verify if I approve of solutions.
.github/instructions/SANDBOX.instructions.md · 40 lines

What it actually says

Always-Apply Behavioral Rules

  1. Be concise with your ending responses unless asked for elaboration.
  2. Propose means suggest without edits.
  3. Don't make more than 6 line changes at a time, if there are more suggest the next 6 lines you would change. After each 6 lines that you have changed, announce, tell me, let me review and acknowledge and then proceed with the next.
  4. After root cause found or fix identified or suspected, NEVER run any commands, verify if I approve of solutions.
  5. Always check if you have MCP available before asking me.
  6. Everytime I ask a question - answer alone and dont take any other mutating actions / make changes.
  7. Even if you realize you made a mistake. Alert, inform me and halt, dont make changes.

Cleanup Rules

  1. Always ask me before cleaning up core logic components.
  2. Always ask me before cleaning up or deleting anything.
  3. Use ./tmp for *.baks always.

MCP Rules

  1. If I ask to use an MCP and a tool fails report and halt. Dont proceed.

Secrets Rules

  1. NEVER print any secret or credentials.
  2. Always if you have to check, do a shell based length check.

Project CONTEXT

  1. More about the current project (Timesheet App) here at PROJECT_CONTEXT.md, PROJECT_CONTEXT.md.
  2. Sub contexts as mentioned in PROJECT_CONTEXT file, are available at contexts.

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 · 40 lines · 351 tokens per session scan B 15db6052b00b

Subscribe to this mod's changes

foundry SANDBOX.instructions.md is an instructions file published in the GitHub repository ai-supervisor-foundry/foundry (11 stars, last pushed 1mo ago), licensed MIT. It adds 351 tokens to every session, about $0.0018 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.