agentmods.dev

foundry: Instructions file for GitHub Copilot

.github/instructions/SANDBOX.instructions.md

foundry SANDBOX.instructions.md is an instructions file for GitHub Copilot from bifrost5/foundry. It costs 351 tokens per session, scanned B, a copy of foundry SANDBOX.instructions.md, MIT.

A set of project instructions for Foundry's sandbox environment. It tells an AI coding assistant how to make small approved changes, handle cleanup, respond to tool failures, protect secrets, and use project context.

In plain words
What is it for?
Use it to guide an AI coding assistant working on the Foundry Timesheet App and its sandbox files.
Why use it?
It limits unintended changes while an assistant works in the sandbox. It also makes approval, cleanup, and error-handling expectations explicit.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is bifrost5/foundry's own configuration. It tells GitHub Copilot how to work on foundry 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 foundry configures →

not rated 12repo 3mo ago B scan 351 tokens copy · 100% MIT
View source ↗ bifrost5/foundry
Reuse

Borrowing it

Nothing to install: this file belongs to bifrost5/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/bifrost5/foundry/main/.github/instructions/SANDBOX.instructions.md
Clone the repo
git clone --depth 1 https://github.com/bifrost5/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/bifrost5/foundry/sandbox/github.svg)](https://agentmods.dev/instructions/bifrost5/foundry/sandbox)
Your own site
<a href="https://agentmods.dev/instructions/bifrost5/foundry/sandbox"><img src="https://agentmods.dev/badge/instructions/bifrost5/foundry/sandbox/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.

agentmods 80×15 button for foundry SANDBOX.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bifrost5/foundry/sandbox"><img src="https://agentmods.dev/badge/instructions/bifrost5/foundry/sandbox.svg" alt="Reviewed on agentmods" width="80" 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. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00351 $0.00351
Opus 5.5 $0.00140 $0.00140
Sonnet 5.5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured today against content hash 15db6052b00b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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.
Origin

This is a copy

100% identical to foundry SANDBOX.instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.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. today 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 bifrost5/foundry (12 stars, last pushed 3mo ago), licensed MIT. It adds 351 tokens to every session, about $0.0014 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). It is 100% identical to foundry SANDBOX.instructions.md, differing in 0 lines, and is treated as a copy.

Building agentsagentaicontrol-planefoundrysoftware-factorysupervisor
Related

foundry SANDBOX.instructions.md compared with instructions from other repositories

foundry SANDBOX.instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
foundry SANDBOX.instructions.mdbifrost5/foundryInstructions file123mo agoMITB351GitHub Copilot
runtm copilot-instructions.mdruntm-ai/runtmInstructions file3032d agononeA297GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot