What is celln AGENTS.md?

A set of project rules for AI coding agents working on a specific codebase. An AGENTS.md file records vocabulary, technical constraints, and working practices the agent must follow.

Use it to guide coding agents working on the sympozium-ai/celln project, including its terminology, security boundaries, virtual machines, networking, and execution rules.

It reduces mistakes caused by using the wrong names, assuming unsupported hardware behavior, or violating architecture and compatibility requirements. The rules give the agent project-specific context before it changes code.

How sympozium-ai/celln configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sympozium-ai/celln. 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/sympozium-ai/celln/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sympozium-ai/celln

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sympozium-ai/celln/agents-md/github.svg)](https://agentmods.dev/instructions/sympozium-ai/celln/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sympozium-ai/celln/agents-md"><img src="https://agentmods.dev/badge/instructions/sympozium-ai/celln/agents-md/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/instructions/sympozium-ai/celln/agents-md"><img src="https://agentmods.dev/badge/instructions/sympozium-ai/celln/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 770 This file is loaded in full into every session.

When invoked 770 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00770	$0.00770
Opus 5.5	$0.00308	$0.00308
Sonnet 5.5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 2mo ago against content hash 477a2b9ed85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

celln 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 2mo 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — house rules

Read this before touching the code. It inherits the constraints and vocabulary of the design corpus in docs/.

Vocabulary (non-negotiable)

mote = the substrate at rest (stripped kernel + pilot). cell = a live, sealed, tool-loaned mote. Every cell is a sealed mote. Never use the two interchangeably. Full glossary: docs/NAMES_AND_CONVENTIONS.md.
Components: assay (host daemon, where the distro lives), warden (per-cell VMM), pilot (in-cell supervisor). 1 warden : 1 microVM : 1 cell.

Constraints (from the build plan §1)

The guest never boots in the hot path — spawn is a CoW fork of a warm mote.
No in-kernel network stack; pilot-fetch sends bounded HTTPS requests over four dedicated PIO ports (0x500-0x503) to the host proxy.
The filesystem has no authority to run code — exec is by content hash against a signed manifest.
Tool code is unwritable from the guest side (stage-2 sealing).
Authority only shrinks — the ratchet is host-enforced in warden.
Compatibility is a feature — every ABI break is a silent latency tax.

Working rules

Never fake a hardware guarantee. If a backend can't provide a property, return Unsupported (see warden::vmm::kvm). A stub that lies is worse than a stub that refuses.
Prefer measurement over assertion. Performance claims become committed numbers, not comments.
Reduce guest attack surface and stay reversible when choosing between implementations; keep the rationale close to the code it affects.
Rust for code, Make for orchestration, shell for glue. No Python.
make ci must stay green: fmt-check build test.

Where things are

Trust core (no I/O): crates/celln-manifest
Store: crates/celln-store
Cell spec parsing + validation: crates/celln-spec
Grading, tiered resolution + CLI: crates/celln-assay
Build plane (rebuild + reproduce): crates/celln-forge
The celln CLI users actually run: crates/celln-cli
Ratchet + VMM trait/backends: crates/celln-warden (vmm/kvm.rs real KVM, vmm/boot.rs stock-kernel boot)
Exec gate + lanes + explain + demos: crates/celln-pilot
Guest-side code: guest/init/init.c (freestanding, no libc); guest images built by scripts/mkinitramfs.sh and scripts/mktoolfs.sh
Hardware checks: celln verify; measurements: make bench-kvm (local output under target/celln-bench/)

Read the full file on GitHub · 58 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.

2mo ago Changed · -1 lines 477a2b9ed85e
2mo ago Changed · +1 lines · +19 tokens per session 2425b1f143f6
2mo ago First seen · 58 lines · 751 tokens per session scan A 0d239d7a2ff8

Subscribe to this mod's changes

celln AGENTS.md is an instructions file published in the GitHub repository sympozium-ai/celln (62 stars, last pushed 4d ago), licensed Apache-2.0. It adds 770 tokens to every session, about $0.0031 per session on Opus 5.5. 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.

celln AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
celln AGENTS.mdsympozium-ai/celln	Instructions file	62	4d ago	Apache-2.0	A	770	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

celln: Instructions file for Codex