remote-dev-containers AGENTS.md

Repository instructions for remote-dev-containers, covering its architecture, security rules, runtime behavior, dependencies, and required pull-request process.

In plain words
What is it for?
Use them when modifying container isolation, launchers, runtime admission, security hardening, Codex approval modes, updates, legal notices, or related documentation.
Why use it?
They identify the authoritative project decisions and issues to check before changing runtime design or support claims.

Instructions file for CodexOpenCode

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/experience83/remote-dev-containers/agents-md
Clone the repo
git clone --depth 1 https://github.com/eXPerience83/remote-dev-containers

Made for: Codex, OpenCode.

Per session 1,864 This file is loaded in full into every session.
When invoked 1,864 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 $0.01864 $0.01864
Opus 5 $0.00932 $0.00932
Sonnet 5 $0.00373 $0.00373
Haiku 4.5 $0.00186 $0.00186

Measured yesterday against content hash 2a69fa1a14c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remote-dev-containers 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 yesterday.

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 · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

These instructions apply to the entire repository unless a more specific nested AGENTS.md is added later.

Sources of truth

Before changing runtime architecture or support claims, read the current GitHub issues rather than relying on stale prose in a prompt:

  • #31 is the roadmap and dependency tracker.
  • #24 is the completed single-image, single-stack, isolated-service architecture contract.
  • #25 is the role-neutral runtime and launcher epic.
  • #26 and #53 define the third-party notice and recurring legal-review process.
  • #36 records the completed TrueNAS outer-isolation and no-Bubblewrap decision.
  • #42 covers later outer-container hardening and cross-service canaries.
  • #46 covers configurable Codex approval modes.
  • #92 owns broad English/Spanish documentation and implementation-status synchronization.
  • #96 owns compatible official-source Antigravity runtime admission and its reviewed/review-pending/damaged states.
  • #83 owns scheduled Antigravity detection and human-review PR automation after #96; it must not gate runtime availability.
  • #103 owns optional explicit Codex runtime updates while preserving the immutable bundled fallback.

If an issue and repository code disagree, report the discrepancy before expanding scope.

Mandatory PR discipline

  • Work on a branch and open a pull request. Never push implementation changes directly to main.
  • Keep one focused objective per PR. Do not combine runtime migration, launcher routing, legal review, vendor installation, persistence migration, and real-login evidence.
  • Stop and ask before adding a new subsystem or changing the agreed PR boundary.
  • Do not build universal Dockerfile, shell, package-manager, license, or static-analysis parsers. Prefer explicit mappings and bounded validators for known repository inputs.
  • Do not introduce speculative support for optional agents. Missing optional roles must remain unavailable and must never download silently.
  • Do not change unrelated dependency pins, generated legal evidence, image names, Compose layouts, or persistent mounts unless the issue and PR explicitly include them.
  • Preserve compatibility wrappers until their removal point is documented and reviewed.

Read the full file on GitHub · 129 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. yesterday First seen · 129 lines · 1,864 tokens per session scan A 2a69fa1a14c9

Subscribe to this mod's changes

remote-dev-containers AGENTS.md is an instructions file published in the GitHub repository eXPerience83/remote-dev-containers (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,864 tokens to every session, about $0.0093 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 2026-08-31.