Borrowing it
Nothing to install: this file belongs to amyodov/yet-another-agentic-chat. 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/amyodov/yet-another-agentic-chat/main/CLAUDE.mdgit clone --depth 1 https://github.com/amyodov/yet-another-agentic-chatWrote 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/amyodov/yet-another-agentic-chat/claude-md)<a href="https://agentmods.dev/instructions/amyodov/yet-another-agentic-chat/claude-md"><img src="https://agentmods.dev/badge/instructions/amyodov/yet-another-agentic-chat/claude-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 | $0.07387 | $0.07387 |
| Opus 5 | $0.03694 | $0.03694 |
| Sonnet 5 | $0.01477 | $0.01477 |
| Haiku 4.5 | $0.00739 | $0.00739 |
Grade B, and why
yet-another-agentic-chat CLAUDE.md scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
until the project is trusted in `~/.codex/config.toml`, which is silent except for one line in the app-server's How it starts
The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
See README.md for what YAAC does. This file is about working on it.
README.md also tracks features — what is in the current version and what is planned. Update its Status section
whenever you ship or defer something; it is the only record, as there is no separate roadmap or issue tracker.
Vocabulary
| Term | Meaning |
|---|---|
| frontend | The MCP server: tool definitions, no state. |
| backend | In-process module: ZMQ sockets, inbox, roster cache. |
| hat | Whichever backend won the bind. Confers the job of passing messages along, and nothing else. |
| participant | Any backend on a channel, wearing the hat or not. |
| membership | One (channel, name) a process holds. A process may hold several. |
| connection id | A membership's routing id, returned by join_channel and used to address it. |
| channel | A named conversation. Addressing, not isolation. |
| name | A user-chosen name within a channel. Raw UTF-8. |
| routing_id | ULID set as the ZMQ ROUTING_ID; zmq_routing_id on the wire. |
| address | {name, zmq_routing_id}. How participants are named on the wire — never a bare string. |
ZMQ's own words stay ZMQ's own, prefixed: zmq_routing_id, not a YAAC synonym for it.
"frontend" and "backend" are relative to the MCP tool surface, not web layers. "channel" always means a YAAC channel, never the Claude Code feature of the same name.
Layout
src/yaac/
frontend.py MCP tool definitions, and the tool a hook calls
backend.py sockets, bind election, receive loops, connection state
hat.py routing table, whois, roster, bounce, session directory
protocol.py envelope + control messages, serialization
notices.py each session's own WebSocket: what a watcher streams and a hook asks
directory.py the client side of `sessions` — who is running here, asked at the rendezvous point
hook.py `yaac-hook`, the program Codex runs because its hooks cannot call a tool
wake.py starting a turn in an idle Codex session through its app-server
processes.py the process tree: ancestry, and command lines, on all three OSes
chat.py the terminal client's entry point; imports textual only once it knows it is there
chat_app.py the terminal client itself
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.
- 3d ago Changed · +15 lines · +293 tokens per session 15ab395cf47a
- 7d ago First seen · 400 lines · 7,094 tokens per session scan B b25c440bcaa7
yet-another-agentic-chat CLAUDE.md is an instructions file published in the GitHub repository amyodov/yet-another-agentic-chat (4 stars, last pushed 2d ago), licensed MIT. It adds 7,387 tokens to every session, about $0.0369 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.