SageFs AGENTS.md

SageFs AGENTS.md is an instructions file for Codex, OpenCode from WillEhrendreich/SageFs. It costs 1,552 tokens per session, scanned A, original, MIT.

Project instructions for SageFs, a coding environment with a long-running background service, a code session, a tool server, and a dashboard.

In plain words
What is it for?
They are for guiding agents working on SageFs projects, especially when starting the service and verifying it with a screenshot or time-limited check.
Why use it?
They prevent an agent from waiting forever for a service that is designed to keep running and set rules for checking whether it is ready.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

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/willehrendreich/sagefs/agents-md
Clone the repo
git clone --depth 1 https://github.com/WillEhrendreich/SageFs

Made for: Codex, OpenCode.

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 SageFs AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/willehrendreich/sagefs/agents-md.svg)](https://agentmods.dev/instructions/willehrendreich/sagefs/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/willehrendreich/sagefs/agents-md"><img src="https://agentmods.dev/badge/instructions/willehrendreich/sagefs/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,552 This file is loaded in full into every session.
When invoked 1,552 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 5.1 $0.01552 $0.01552
Opus 5 $0.00776 $0.00776
Sonnet 5 $0.00310 $0.00310
Haiku 4.5 $0.00155 $0.00155

Measured 2d ago against content hash af9dd3751b2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

SageFs AGENTS.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.

AGENTS.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SageFs — Coding Agent Guidelines

STOP — Read This Before Anything Else

The SageFs daemon is a long-running process that never exits on its own. It hosts the FSI session, MCP server, and dashboard on ports 37749/37750. You will be tempted to wait for it. DO NOT.

The cardinal rule, stated three times because it is the only thing you keep getting wrong:

  1. NEVER narrate a wait to the user. After starting a daemon, do not write "verifying" or "checking" or "started" and then stop. The next thing you produce must be a tool result — specifically a screenshot, an HTTP probe with a hard timeout, or the next concrete step. A chat message that is not a result or a question is the failure mode.

  2. NEVER call a command that blocks on the daemon's lifetime. Wait-Process, Start-Process -Wait, waiting for a process to exit, taskkill /T /F on the daemon while also awaiting the result — all of these will hang forever because the daemon is not supposed to exit.

  3. NEVER treat Start-Sleep as "wait for the daemon to be ready" without a follow-up tool call in the same turn. Start-Sleep 3 followed by a chat message is the same hang, just shorter. Start-Sleep 3 followed by a screenshot is fine. The sleep is not the problem. The text after the sleep is the problem.

Concrete patterns:

  • Starting the daemon: one Start-Process ... -WindowStyle Hidden (no -Wait), one Start-Sleep -Seconds 3 for warmup, then the next tool call is the screenshot. Nothing in between.
  • Verifying the daemon is up: Invoke-WebRequest -TimeoutSec 3 with a hard timeout. If it returns, great. If it throws a timeout exception, kill the request and report the state. Do not retry indefinitely.
  • Killing the daemon: Get-Process -Name "SageFs" | Stop-Process -Force returns immediately. Never combine that with a Wait-Process.
  • The "is it up" check is the screenshot. Not a chat message, not a sleep, not a status probe. The screenshot.

If you catch yourself writing a sentence that contains "waiting", "let me check", "verifying", "starting up", or "should be ready" between starting a process and your next tool call, stop. Skip the sentence. Make the tool call.

Read the full file on GitHub · 111 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 Changed · +2 lines af9dd3751b2d
  2. 6d ago First seen · 109 lines · 1,552 tokens per session scan A 7b31fafe4bd4

Subscribe to this mod's changes

SageFs AGENTS.md is an instructions file published in the GitHub repository WillEhrendreich/SageFs (70 stars, last pushed yesterday), licensed MIT. It adds 1,552 tokens to every session, about $0.0078 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.