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.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 | $0.12504 | $0.12504 |
| Opus 5 | $0.06252 | $0.06252 |
| Sonnet 5 | $0.02501 | $0.02501 |
| Haiku 4.5 | $0.01250 | $0.01250 |
Grade D, and why
aicontainer AGENTS.md scanned grade D with 4 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 7d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
final `FROM` is aicontainer: build steps execute as root and can replace Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
`100.100.100.200/32`, `fe80::/10`, and `fd00:ec2::254`. It is independent of Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`fetch_latest_version()` is bounded (`curl --max-time`, npm-view fallback) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`spawnSync`s it, and `throw`s on exit 2. Root-managed How it starts
The opening of the file, as written. The whole thing — 839 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) working on aicontainer itself.
Users running aicontainer in their projects start at README.md.
CLAUDE.md is a thin pointer to this file — keep that arrangement; new
agent-facing notes go here.
Convention: "guarded by the '…' test" below names a CLI/smoke test present in both workflows. When you change the behavior, extend the test — never weaken it.
Repository layout
aic— the host-side bash CLI, single file. Exposed as npm bin (aic,aicontainer) and~/.aicontainer/aicfor git installs. Finds its template via$AIC_HOME(defaults to the script's directory after symlink-following).template/— copied into a project's.devcontainer/byaic init/aic sync; the source of truth for what lands in user repos.Dockerfile,post-create.py,hooks/,aic-firewall,aic-chown-volumes,aic-lock-user-config,.zshrc,.gitignorehooks/: the shared guardrailpre-tool-use.sh, the thin OpenCode adapteropencode-guardrail.js, and the opt-in metadata-only Claude/Codex lifecycle relayagent-status.py— all copied root-owned to/etc/aic/hooks/.docker-compose.pull.yml(default mode),docker-compose.build.yml(--buildmode)README.md— copied into every project's.devcontainer/in both modes; a managed guide to the do-not-edit vs project-owned split. Keep its two lists in sync withapply_template()and the project-owned files..gitignore— copied in both modes and contains only.env..envitself is atomically generated per host/context; it holds the socket, runtime user, path-free project identity, and host-owned status relay mode. It is a managed control file, not a template asset or project-owned override.
.github/workflows/rebuild.yml— security-refresh track: relevant template/CLI/test/ package pushes tomain, weekly cron,workflow_dispatch. Publishes GHCR:latest+:weekly-YYYY-VV; never npm.release.yml— release track:v*tag push (orworkflow_dispatchon a tag ref) only. Ensures immutable:vX.Y.Z+ npm artifacts exist, then conservatively promotes mutable latest channels.
tests/— host CLI and privileged-helper regression tests run before both real-devcontainer workflow smoke suites. Security fixes normally add a fast host fixture here and a runtime assertion in both workflows.package.json— itsversionis the source of truth for the GHCR tagaic initpins. Never bump it by hand; usenpm version(see "Releasing").CHANGELOG.md— hand-maintained (Keep a Changelog format); source of the GitHub Release notes and a release precondition.scripts/promote-changelog.mjs— zero-dep helper run bynpm version: promotes## [Unreleased]to the new version (date + compare links). Never generates content..githooks/pre-push— local mirror of the CI changelog gate; opt-in viagit config core.hooksPath .githooks.
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.
- 7d 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 (20 stars, last pushed 2d ago), licensed MIT. It adds 12,504 tokens to every session, about $0.0625 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.