A set of working rules for an AI coding-agent system that coordinates persistent software projects. It limits changes, requires approval before some actions, and tells the agent when to stop.

Use it to control how an agent answers questions, proposes changes, checks available tools, and proceeds through small reviewed edits.

It helps prevent unapproved edits, accidental commands, and work continuing after a mistake or uncertain diagnosis.

always — Cursor rule for Cursor by bifrost5/foundry

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.

Clone the repo

git clone --depth 1 https://github.com/bifrost5/foundry

Made for: Cursor.

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/rules/bifrost5/foundry/always/github.svg)](https://agentmods.dev/rules/bifrost5/foundry/always)

Your own site

<a href="https://agentmods.dev/rules/bifrost5/foundry/always"><img src="https://agentmods.dev/badge/rules/bifrost5/foundry/always/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/rules/bifrost5/foundry/always"><img src="https://agentmods.dev/badge/rules/bifrost5/foundry/always.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 167 This file is loaded in full into every session.

When invoked 167 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.

Model	Per session	Once invoked
Fable 5.1	$0.00167	$0.00167
Opus 5.5	$0.00067	$0.00067
Sonnet 5.5	$0.00033	$0.00033
Haiku 4.5	$0.00017	$0.00017

Measured today against content hash aadfe798b111, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

always 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 always — 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.

.cursor/rules/always.mdc · 10 lines

What it actually says

Be concise with your ending responses unless asked for elaboration.
Propose means suggest without edits.
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.
After root cause found or fix identified or suspected, NEVER run any commands, verify if I approve of solutions.
Always check if you have MCP available before asking me.
Everytime I ask a question - answer alone and dont take any other mutating actions / make changes.
Even if you realize you made a mistake. Alert, inform me and halt, dont make changes.

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.

today First seen · 10 lines · 167 tokens per session scan B aadfe798b111

Subscribe to this mod's changes

always is a cursor rule published in the GitHub repository bifrost5/foundry (12 stars, last pushed 3mo ago), licensed MIT. It adds 167 tokens to every session, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). It is 100% identical to always, differing in 0 lines, and is treated as a copy.

Building agents agent ai control-plane foundry software-factory supervisor

always next to 6 cursor rules from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
alwaysbifrost5/foundry	Cursor rule	12	3mo ago	MIT	B	167	Cursor
contextsai-supervisor-foundry/foundry	Cursor rule	12	3mo ago	MIT	A	5	Cursor
supervisor-specsai-supervisor-foundry/foundry	Cursor rule	12	3mo ago	MIT	A	167	Cursor
cleanupai-supervisor-foundry/foundry	Cursor rule	12	3mo ago	MIT	A	9	Cursor
secretsai-supervisor-foundry/foundry	Cursor rule	12	3mo ago	MIT	A	4	Cursor
task-lifecycleai-supervisor-foundry/foundry	Cursor rule	12	3mo ago	MIT	A	32	Cursor
docsai-supervisor-foundry/foundry	Cursor rule	12	3mo ago	MIT	A	23	Cursor

always