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/willehrendreich/sagefs/agents-mdgit clone --depth 1 https://github.com/WillEhrendreich/SageFsWrote 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/willehrendreich/sagefs/agents-md)<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>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 | $0.01552 | $0.01552 |
| Opus 5 | $0.00776 | $0.00776 |
| Sonnet 5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
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.
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:
-
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.
-
NEVER call a command that blocks on the daemon's lifetime.
Wait-Process,Start-Process -Wait, waiting for a process to exit,taskkill /T /Fon the daemon while also awaiting the result — all of these will hang forever because the daemon is not supposed to exit. -
NEVER treat
Start-Sleepas "wait for the daemon to be ready" without a follow-up tool call in the same turn.Start-Sleep 3followed by a chat message is the same hang, just shorter.Start-Sleep 3followed 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), oneStart-Sleep -Seconds 3for warmup, then the next tool call is the screenshot. Nothing in between. - Verifying the daemon is up:
Invoke-WebRequest -TimeoutSec 3with 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 -Forcereturns immediately. Never combine that with aWait-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.
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.
- 2d ago Changed · +2 lines af9dd3751b2d
- 6d ago First seen · 109 lines · 1,552 tokens per session scan A 7b31fafe4bd4
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.
Other instructions, from other repositories
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.