Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/indreamer/telegram-codex-bridge/agents-mdgit clone --depth 1 https://github.com/InDreamer/telegram-codex-bridgeWhat 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 | $0.02218 | $0.02218 |
| Opus 5 | $0.01109 | $0.01109 |
| Sonnet 5 | $0.00444 | $0.00444 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade B, and why
telegram-codex-bridge AGENTS.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.
- `feishu-docs-mcp status` - report whether the `feishuDeveloperDocs` MCP block is present in `~/.codex/config.toml` How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent router for telegram-codex-bridge.
Current shipped truth in this repo is still Telegram-first. Future repository direction may describe a broader Codex Bridge Core with additional platform packs. Keep those two truths separated.
Goal: let a coding agent build a useful mental index of the repo without preloading the repo. The default path is:
- read this file
- read one domain agent
- read one leaf doc or one narrow code file
That is the whole default retrieval path.
Retrieval Contract
Maximum default depth: 3 layers.
- Layer 1:
AGENTS.md(choose the domain) - Layer 2: one domain agent such as
docs/AGENTS.mdorsrc/AGENTS.md - Layer 3: one leaf doc or one narrow source file
Do not read sibling docs or sibling code files "just in case". Expand only when the active task is cross-cutting, conflicting, or explicitly architectural.
Source Priority
Use sources in this order:
- active user instruction
- current docs in
docs/product/,docs/architecture/,docs/operations/, anddocs/generated/current-snapshot.md - current implementation in
src/ - protocol evidence in
docs/research/ - planning and history in
docs/roadmap/,docs/future/,docs/plans/, anddocs/archive/
Do not treat planning/history as shipped behavior. Do not treat protocol capability as proof that Telegram UX already exposes it.
Domain Router
| If the task is mainly about | Read next |
|---|---|
| current docs, intended behavior, product/runtime/ops questions | docs/AGENTS.md |
| current implementation, code ownership, refactors, bug fixes | src/AGENTS.md |
| GitHub install entry scripts | scripts/AGENTS.md |
| bundled Codex skills | skills/AGENTS.md |
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 First seen · 188 lines · 2,218 tokens per session scan B a5103bc7c30d
telegram-codex-bridge AGENTS.md is an instructions file published in the GitHub repository InDreamer/telegram-codex-bridge (26 stars, last pushed 3mo ago), licensed MIT. It adds 2,218 tokens to every session, about $0.0111 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 2026-08-30.
Other instructions, from other repositories
LangBot AGENTS.md
Instructions for langbot-app/LangBot, covering agents.md, quick facts, essential commands, where to look and cross-repo sdk work.
Alita_Robot AGENTS.md
Instructions for Divkix/Alita_Robot, covering repository guidelines, maintaining this file, 0. maintaining this document (read first), 1. mental model — how it fits together and 2. project structure.
telegram-search copilot-instructions.md
Copilot instructions for groupultra/telegram-search, covering copilot instructions for telegram-search, architecture essentials, dev workflows, conventions and patterns and where to look for examples.
telegram-search AGENTS.md
AGENTS.md instructions for groupultra/telegram-search, covering project coded agent guide, tech stack (by surface), structure & responsibilities, key path index (what lives where) and commands (pnpm with filters).
telegram-bot AGENTS.md
Instructions for vendelieu/telegram-bot, covering agents.md, dev environment, testing, project structure and key conventions.
telegram-search CLAUDE.md
Claude Code instructions for groupultra/telegram-search, a project described as: 🔍 导出并模糊搜索 Telegram 聊天记录 | Export and fuzzy search your Telegram chat history.