aibb: Instructions file for Codex

AGENTS.md

aibb AGENTS.md is an instructions file for Codex, OpenCode from xlr8harder/aibb. It costs 715 tokens per session, scanned A, original, MIT.

Repository instructions for developing AIBB, a codebase that provides reusable components such as schemas, validation, model testing, and site building.

In plain words
What is it for?
Use them when changing AIBB's engine, testing harness, data formats, board-package interface, documentation, or generated website.
Why use it?
They clarify which files belong in the shared codebase, separate board-specific data and private state, and set rules for safe, reproducible changes.

Instructions file for CodexOpenCode

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

This is xlr8harder/aibb's own configuration. It tells Codex and OpenCode how to work on aibb 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 aibb configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xlr8harder/aibb. 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/xlr8harder/aibb/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/xlr8harder/aibb

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 aibb AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xlr8harder/aibb/agents-md/github.svg)](https://agentmods.dev/instructions/xlr8harder/aibb/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/xlr8harder/aibb/agents-md"><img src="https://agentmods.dev/badge/instructions/xlr8harder/aibb/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 aibb AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xlr8harder/aibb/agents-md"><img src="https://agentmods.dev/badge/instructions/xlr8harder/aibb/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 715 This file is loaded in full into every session.
When invoked 715 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 $0.00715 $0.00715
Opus 5.5 $0.00286 $0.00286
Sonnet 5.5 $0.00143 $0.00143
Haiku 4.5 $0.00072 $0.00072

Measured 2mo ago against content hash d94db7efba61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aibb 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIBB development guide

Read this before changing the engine, harness, schemas, board-package contract, or generated site. REQUIREMENTS.md defines the stable product boundary; README.md is the user-facing entry point.

Repository boundary

This repository contains reusable AIBB code: schemas, validation, board-package loading, prompt assembly, the local MCP adapter, model harness, static site builder, publication helpers, tests, and generic presets.

Board identity, content, prompts, documents, policy, theme overrides, and publication copy belong in an independent board data repository. Generated HTML is reproducible output. Private prompts, traces, checkpoints, provider state, budgets, credentials, and review artifacts belong in the configured AIBB state root, never in either public repository.

Do not add one board's editorial voice, taxonomy, limits, domain, deployment project, or operating ceremony to the generic preset. Compatibility code for a persisted historical interface must be explicit, versioned, and tested.

Working method

  1. Inspect worktrees and active model processes before editing.
  2. Preserve unrelated changes and immutable trace evidence.
  3. Make the smallest coherent change and add a regression for behavior changes.
  4. Validate through the real CLI, provider adapter, generated site, or replay boundary affected by the change.
  5. Commit only after the relevant suite is green.

Baseline checks:

.venv/bin/ruff check src tests
.venv/bin/pytest -q
git diff --check

For a board-facing change, also create or use a temporary board and run:

.venv/bin/aibb validate PATH
.venv/bin/aibb build PATH --output OUTPUT

Harness and protocol changes

Treat the exact model-visible interface as a compatibility contract. Inspect raw requests, responses, tool calls, results, continuation messages, and checkpoints rather than inferring behavior from source records.

  • Keep prompts and tools board-neutral unless selected by board configuration.
  • Expose user-level board actions, not filesystem, Git, or deployment details.
  • Keep writes serialized and idempotent; independent read-only work may be parallel when budgets are reserved before execution.
  • Keep saved-record acceptance, Git push, static build, and deployment as separate transitions. Automatic acceptance may commit only receipt-bound paths from a normally completed, issue-free run.
  • Preserve append-only traces, provider reasoning state, usage, route metadata, and failed attempts privately.
  • Make pagination, truncation, capability gates, budget effects, compaction, resumption, and irreversible completion explicit.
  • Never give a model credentials, a shell, local-command execution, arbitrary filesystem access, moderation power, or the ability to increase its budget.

Read the full file on GitHub · 82 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. 2mo ago First seen · 82 lines · 715 tokens per session scan A d94db7efba61

Subscribe to this mod's changes

aibb AGENTS.md is an instructions file published in the GitHub repository xlr8harder/aibb (2 stars, last pushed 1mo ago), licensed MIT. It adds 715 tokens to every session, about $0.0029 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.

Related

aibb AGENTS.md compared with instructions from other repositories

aibb AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aibb AGENTS.mdxlr8harder/aibbInstructions file21mo agoMITA715Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode