agentmods.dev

ccbot: Instructions file for Claude Code

CLAUDE.md

ccbot CLAUDE.md is an instructions file for Claude Code from six-ddc/ccbot. It costs 705 tokens per session, scanned B, a copy of ccbot AGENTS.md, MIT.

A repository instruction file for ccbot, a Python bot that connects Telegram forum topics to Claude Code sessions through tmux. It records the project’s commands and design constraints.

In plain words
What is it for?
It guides development, linting, type checking, formatting, session routing, Telegram message sending, and restarting the ccbot service.
Why use it?
It prevents changes that would break the one-topic-to-one-session routing model, message handling, or required quality checks.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is six-ddc/ccbot's own configuration. It tells Claude Code how to work on ccbot 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 ccbot configures →

not rated 277repo 4mo ago B scan 705 tokens copy · 95% MIT
View source ↗ six-ddc/ccbot
Reuse

Borrowing it

Nothing to install: this file belongs to six-ddc/ccbot. 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/six-ddc/ccbot/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/six-ddc/ccbot

Made for: Claude Code.

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 ccbot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/six-ddc/ccbot/claude-md/github.svg)](https://agentmods.dev/instructions/six-ddc/ccbot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/six-ddc/ccbot/claude-md"><img src="https://agentmods.dev/badge/instructions/six-ddc/ccbot/claude-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 ccbot CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/six-ddc/ccbot/claude-md"><img src="https://agentmods.dev/badge/instructions/six-ddc/ccbot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 705 This file is loaded in full into every session.
When invoked 705 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 95% copy Near-identical to another mod 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 $0.00705 $0.00705
Opus 5.5 $0.00282 $0.00282
Sonnet 5.5 $0.00141 $0.00141
Haiku 4.5 $0.00071 $0.00071

Measured 2mo ago against content hash 6a699a0daa05, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

ccbot 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Or manually in `~/.claude/settings.json`:
Origin

This is a copy

95% identical to ccbot AGENTS.md — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

ccmux — Telegram bot that bridges Telegram Forum topics to Claude Code sessions via tmux windows. Each topic is bound to one tmux window running one Claude Code instance.

Tech stack: Python, python-telegram-bot, tmux, uv.

Common Commands

uv run ruff check src/ tests/         # Lint — MUST pass before committing
uv run ruff format src/ tests/        # Format — auto-fix, then verify with --check
uv run pyright src/ccbot/             # Type check — MUST be 0 errors before committing
./scripts/restart.sh                  # Restart the ccbot service after code changes
ccbot hook --install                  # Auto-install Claude Code SessionStart hook

Core Design Constraints

  • 1 Topic = 1 Window = 1 Session — all internal routing keyed by tmux window ID (@0, @12), not window name. Window names kept as display names. Same directory can have multiple windows.
  • Topic-only — no backward-compat for non-topic mode. No active_sessions, no /list, no General topic routing.
  • No message truncation at parse layer — splitting only at send layer (split_message, 4096 char limit).
  • MarkdownV2 only — use safe_reply/safe_edit/safe_send helpers (auto fallback to plain text). Internal queue/UI code calls bot API directly with its own fallback.
  • Hook-based session tracking — SessionStart hook writes session_map.json; monitor polls it to detect session changes.
  • Message queue per user — FIFO ordering, message merging (3800 char limit), tool_use/tool_result pairing.
  • Rate limiting — AIORateLimiter(max_retries=5) on the Application (30/s global). On restart, the global bucket is pre-filled to avoid burst against Telegram's server-side counter.

Code Conventions

  • Every .py file starts with a module-level docstring: purpose clear within 10 lines, one-sentence summary first line, then core responsibilities and key components.
  • Telegram interaction: prefer inline keyboards over reply keyboards; use edit_message_text for in-place updates; keep callback data under 64 bytes; use answer_callback_query for instant feedback.

Read the full file on GitHub · 60 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 · 60 lines · 705 tokens per session scan B 6a699a0daa05

Subscribe to this mod's changes

ccbot CLAUDE.md is an instructions file published in the GitHub repository six-ddc/ccbot (277 stars, last pushed 4mo ago), licensed MIT. It adds 705 tokens to every session, about $0.0028 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 95% identical to ccbot AGENTS.md, differing in 14 lines, and is treated as a copy.

Related

ccbot CLAUDE.md compared with instructions from other repositories

ccbot CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ccbot CLAUDE.mdsix-ddc/ccbotInstructions file2774mo agoMITB705Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode