Borrowing it
Nothing to install: this file belongs to stefanoginella/aicontainer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stefanoginella/aicontainer/main/AGENTS.mdgit clone --depth 1 https://github.com/stefanoginella/aicontainerWrote 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/stefanoginella/aicontainer/agents-md)<a href="https://agentmods.dev/instructions/stefanoginella/aicontainer/agents-md"><img src="https://agentmods.dev/badge/instructions/stefanoginella/aicontainer/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.
<a href="https://agentmods.dev/instructions/stefanoginella/aicontainer/agents-md"><img src="https://agentmods.dev/badge/instructions/stefanoginella/aicontainer/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02210 | $0.02210 |
| Opus 5.5 | $0.00884 | $0.00884 |
| Sonnet 5.5 | $0.00442 | $0.00442 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
aicontainer 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 8d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (and humans) who work on aicontainer. Users who run aicontainer in their projects start at README.md.
aicontainer is a sandbox for autonomous AI tools (Claude Code, Codex, OpenCode) that run in bypass / auto-approve mode. Most code in this repository is a security boundary. The threat model is docs/user/security.md.
Repository map
aic— the entry script of the host-side bash CLI. npm binaic/aicontainer. It loads the modules inlib/aic/from an explicit list, then dispatches the command.lib/aic/— the bash modules of the CLI, one file for each concern. They only define functions and constants.lib/— host-side Node modules thataicruns. Onlynode:built-ins.validate.mjsis the structural validator;validate-cli.mjsruns it.template/— copied into every user project's.devcontainer/byaic init/aic sync. The source of truth for what lands in user repos.tests/— host CLI and privileged-helper regression tests..github/workflows/—rebuild.yml(security-refresh track,:latest),release.yml(release track,v*tags),smoke.yml(shared smoke suite,workflow_callonly).tools/claude-plugin/— the/aicontainer:setupClaude Code plugin.docs/user/— the user guide.docs/contributing/— the contributor guide.
Full layout: docs/contributing/architecture.md.
Read before you change
Load the page for the area before you edit it. Each page holds the rules for its area and the tests that guard them.
| When you touch | Read |
|---|---|
| Dev setup, conventions, local test runs | development.md |
Repository layout, the aic module list and lib/aic/, template/ file list, package contents |
architecture.md |
template/Dockerfile downloads, pins, checksums, GHCR tag pinning |
image-integrity.md |
Drift warnings, update checks, aic initialize CLI lookup |
version-drift.md |
Project name, COMPOSE_PROJECT_NAME, path spelling, migration, .devcontainer/ and .git control paths |
project-identity.md |
validate_project_security() (lib/aic/validation.sh), lib/validate.mjs, lib/trust-hash.mjs, aic trust, diagnostics |
validation.md |
Docker socket in .env, runtime detection, agent-status relay |
host-state.md |
Seed sanitizer, tool homes, post-create resets, aic-auth-sync, volumes, aic signing |
seeds-and-auth.md |
Project-owned override files, docker-compose.override.yml, chown-paths, post-create.project.sh, VS Code files |
project-overrides.md |
Shell startup, personal overlay (rc.zsh, p10k.zsh, statusline.*), AI-tool refresh |
shell-and-overlays.md |
Docker access modes, metadata block, pids_limit |
runtime-policy.md |
template/aic-firewall, hooks, privileged helpers, workflows (the security list below) |
security-review.md |
| A release, the CHANGELOG, the two workflow tracks | releasing.md |
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.
- 8d ago Changed · +5 lines · +90 tokens per session 5aa555e57e25
- 9d ago Changed · -1,065 lines · -16,880 tokens per session scan D → A 83519f573387
- 10d ago Changed · +253 lines · +4,348 tokens per session a8b7a6abc8e6
- 11d ago Changed · +125 lines · +1,999 tokens per session af612af1c253
- 16d ago Changed · +8 lines · +149 tokens per session b87bf088a7bd
- 1mo ago First seen · 839 lines · 12,504 tokens per session scan D 997484f4995e
aicontainer AGENTS.md is an instructions file published in the GitHub repository stefanoginella/aicontainer (21 stars, last pushed 2d ago), licensed MIT. It adds 2,210 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.