agentmods.dev

aihaus-flow: Instructions file for Codex

AGENTS.md

aihaus-flow AGENTS.md is an instructions file for Codex, OpenCode from overdrive-dev/aihaus-flow. It costs 612 tokens per session, scanned A, original, MIT.

A project instruction file for aihaus-flow, a downloadable GitHub package for intent-based developer workflows. It defines the repository map, boundaries, memory files, and validation rules.

In plain words
What is it for?
Use it before changing the package to read its harness contract and map, load only relevant context, preserve existing behavior until tests pass, and run the contract tests.
Why use it?
It keeps package changes aligned with the project's contracts and prevents accidental edits to user content, global instructions, or generated state.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is overdrive-dev/aihaus-flow's own configuration. It tells Codex and OpenCode how to work on aihaus-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aihaus-flow configures →

not rated 5repo changed 5d ago A scan 612 tokens original MIT
View source ↗ overdrive-dev/aihaus-flow
Reuse

Borrowing it

Nothing to install: this file belongs to overdrive-dev/aihaus-flow. 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/overdrive-dev/aihaus-flow/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/overdrive-dev/aihaus-flow

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.

agentmods badge for aihaus-flow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/overdrive-dev/aihaus-flow/agents-md/github.svg)](https://agentmods.dev/instructions/overdrive-dev/aihaus-flow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/overdrive-dev/aihaus-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/overdrive-dev/aihaus-flow/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.

agentmods 80×15 button for aihaus-flow AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/overdrive-dev/aihaus-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/overdrive-dev/aihaus-flow/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 612 This file is loaded in full into every session.
When invoked 612 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00612 $0.00612
Opus 5.5 $0.00245 $0.00245
Sonnet 5.5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 5d ago against content hash 449f8943c3b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aihaus-flow 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 5d 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 · 49 lines

What it actually says

aihaus repository map

aihaus is a downloadable GitHub package, not a website. The publishable payload lives in pkg/; repository-only tests, lab tooling, and docs live outside it.

Before changing the package:

  1. Read pkg/.aihaus/contracts/harness.md for the operating contract.
  2. Read pkg/.aihaus/MAP.md and load only the matching room/contracts.
  3. Treat Markdown project memory and file kanban as truth.
  4. Keep user content and global instruction files untouched.

Implementation rules:

  • Prefer six general roles plus task-specific room context over specialist prompt proliferation.
  • Keep safety/evidence checks as deterministic local tools. Host hooks are optional adapters, never the portable source of truth.
  • Preserve existing behavior until replacement contract tests are green.
  • Do not add a room, role, hook, or state store without a failing lab scenario that demonstrates the need.
  • Generated dogfood state belongs only under ignored .aihaus-lab/.

Validation: node tools/run-contract-tests.mjs.

See docs/architecture.md for boundaries and docs/provenance.md before any deletion wave.

Maintainer runbook:

  • Tasks: owner requests or open issues/PRs on overdrive-dev/aihaus-flow; never record repo facts or tasks in pkg/.aihaus/memory/ (consumer template).
  • main: gh pr merge --squash --delete-branch; package-ci.yml runs the contract suite on Ubuntu/macOS/Windows for package paths only; macOS may queue ~10 min.
  • Release: bump pkg/VERSION, pkg/package.json, pkg/CHANGELOG.md, and README install pins in the PR; after merge push tag v<VERSION> to run package-release.yml; retitle notes AIHAUS FLOW v<VERSION>: <theme> with What changed; Install or update; migration note with opt-out for new defaults.
  • Suite ~30 s; Windows skips one symlink test. The author runs it: the Codex unelevated sandbox on Windows cannot spawn its child processes.
  • Host A/B labs in .aihaus-lab/, at most two Claude sessions at once: run claude -p --model opus --effort ultracode --restricted --strict-mcp-config --tools <tools> --allowedTools <commands> --permission-mode acceptEdits --max-budget-usd 15 with CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS=0 set.
  • Setup replaces package-owned surfaces and never reseeds existing memory; refresh.mjs hashes memory templates. Ship new guidance through MAP, contracts, rooms, roles, or the router, not memory templates.
  • Execution modes apply; no Assignments here, so auto. Profile: README luna.
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. 5d ago Changed · -1 lines · +90 tokens per session 449f8943c3b1
  2. 14d ago Changed · +2 lines · +46 tokens per session 1b348fab9167
  3. 19d ago Changed · +1 lines · +29 tokens per session 937ec67bad9c
  4. 20d ago Changed · +15 lines · +198 tokens per session 90dbbc0cf10f
  5. 1mo ago First seen · 32 lines · 249 tokens per session scan A 8ac4d7413e0e

Subscribe to this mod's changes

aihaus-flow AGENTS.md is an instructions file published in the GitHub repository overdrive-dev/aihaus-flow (5 stars, last pushed 6d ago), licensed MIT. It adds 612 tokens to every session, about $0.0024 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 2026-08-31.

Claude CodeWorkflow Automationagents-mdai-agentsclideveloper-tools
Related

Other instructions, from other repositories

whichrules copilot-instructions.md

Instructions for z35068037/whichrules, a project described as: See exactly which instructions your AI coding agent receives - and where they conflict.

z35068037/whichrules · 21 tokens

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens