agentseek AGENTS.md

Repository instructions for Agentseek, including rules for handling incoming chat messages from Feishu, Telegram, and WeCom.

In plain words
What is it for?
Following Agentseek’s instructions and replying to users through supported chat channels.
Why use it?
It clarifies how the agent should reply when a message comes from one of these chat channels, reducing channel-specific mistakes.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/ob-labs/agentseek/agents-md
Clone the repo
git clone --depth 1 https://github.com/ob-labs/agentseek

Made for: Codex, OpenCode.

Per session 142 This file is loaded in full into every session.
When invoked 142 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00142 $0.00142
Opus 5 $0.00071 $0.00071
Sonnet 5 $0.00028 $0.00028
Haiku 4.5 $0.00014 $0.00014

Measured 3d ago against content hash 8085ec4c3643, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentseek 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 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.

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 · 9 lines

What it actually says

Agentseek Agent Instructions

Chat channels ($feishu, $telegram, $wecom)

When the message context includes a channel tag (e.g. $feishu, $telegram, $wecom) and session/chat metadata, you are on an inbound chat channel.

  • Reply with plain text. The framework delivers it to the user. Do not run shell commands or scripts just to answer the user.
  • Channel-specific send tools (names vary by plugin: e.g. Feishu or Telegram helpers): use them only when you must send a message from inside another tool (e.g. progress during a long task), not for normal turn replies.
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. 3d ago First seen · 9 lines · 142 tokens per session scan A 8085ec4c3643

Subscribe to this mod's changes

agentseek AGENTS.md is an instructions file published in the GitHub repository ob-labs/agentseek (173 stars, last pushed 13d ago), licensed Apache-2.0. It adds 142 tokens to every session, about $0.0007 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 2026-08-30.