ai-conversation-hub: Instructions file for Codex

AGENTS.md

ai-conversation-hub AGENTS.md is an instructions file for Codex, OpenCode from Mark-Libetter/ai-conversation-hub. It costs 407 tokens per session, scanned A, original, MIT.

Repository instructions for AI Conversation Hub, a code project that uses written task handoffs to coordinate development work. They define which project files to read, what work is allowed, and how changes are delivered.

In plain words
What is it for?
They guide agents through reading project context, following task boundaries, preserving existing work, using isolated workspaces when needed, and applying the repository’s Git and validation rules.
Why use it?
They reduce mistakes such as working on the wrong task, overwriting another agent’s changes, or ignoring the project’s required delivery rules.

Instructions file for CodexOpenCode

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

This is Mark-Libetter/ai-conversation-hub's own configuration. It tells Codex and OpenCode how to work on ai-conversation-hub 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 ai-conversation-hub configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Mark-Libetter/ai-conversation-hub. 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/Mark-Libetter/ai-conversation-hub/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Mark-Libetter/ai-conversation-hub

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 ai-conversation-hub AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mark-libetter/ai-conversation-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/mark-libetter/ai-conversation-hub/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 407 This file is loaded in full into every session.
When invoked 407 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 $0.00407 $0.00407
Opus 5 $0.00204 $0.00204
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00041 $0.00041

Measured 8d ago against content hash 87ff3725760c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-conversation-hub 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.

AGENTS.md · 43 lines

What it actually says

Repository relay rules

Treat this repository as the source of current authorization. Conversation history is evidence, not a task contract.

Required read order

Before changing files, read:

  1. PROJECT.md
  2. DECISIONS.md
  3. TASKS.md
  4. The one active handoffs/T-xxx.md

Use AI Conversation Hub only when the contract needs historical evidence. Do not replace the contract with hub_handoff output or a transcript summary.

Task boundaries

  • Work on one active task at a time.
  • Respect Scope, Do not touch, and every acceptance criterion in its handoff.
  • Preserve unrelated and pre-existing worktree changes. Never reset, discard, or rewrite another agent's work to make the tree look clean.
  • Do not run parallel writers in the same worktree. Use verified isolated worktrees for independent parallel tasks; otherwise serialize them.
  • Keep vendor conversation stores read-only and keep the server bound to 127.0.0.1.

Git delivery

  • Record branch, start commit, and dirty state before editing.
  • Follow commit_policy, push_policy, push_target, and integration_owner exactly.
  • Only the named integration owner may push.
  • Never force-push, merge main, create a release, or publish content unless the active handoff explicitly authorizes that exact action.
  • Before handoff or completion, run relevant tests and the project-contract validator, then record evidence, files changed, end commit, and final dirty state.
  • A reviewer receives the handoff, relevant diff, start/end commits, and test evidence—not the coordinator's whole conversation.

Validation

Run at minimum:

py -3 skills/conversation-hub/scripts/validate_project_contract.py .
py -3 -m unittest discover -s tests -q

Add narrower checks required by the active handoff. Do not mark a task done while a required check is failing or delivery remains incomplete.

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. 8d ago First seen · 43 lines · 407 tokens per session scan A 87ff3725760c

Subscribe to this mod's changes

ai-conversation-hub AGENTS.md is an instructions file published in the GitHub repository Mark-Libetter/ai-conversation-hub (3 stars, last pushed 18d ago), licensed MIT. It adds 407 tokens to every session, about $0.0020 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.

Related

Other instructions, from other repositories

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 · 7,296 tokens

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.

openai/codex · 5,153 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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

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.

github/spec-kit · 7,104 tokens