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/ob-labs/agentseek/agents-mdgit clone --depth 1 https://github.com/ob-labs/agentseekWhat 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 | $0.00142 | $0.00142 |
| Opus 5 | $0.00071 | $0.00071 |
| Sonnet 5 | $0.00028 | $0.00028 |
| Haiku 4.5 | $0.00014 | $0.00014 |
Grade A, and why
agentseek AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Agentseek Agent Instructions
Chat channels ($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.
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 · 9 lines · 142 tokens per session scan A 8085ec4c3643
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.
Other instructions, from other repositories
crewAI AGENTS.md
AGENTS.md instructions for crewAIInc/crewAI, covering agent instructions for crewai oss, key guidelines, message content and changing docs.
fastmcp CLAUDE.md
Claude Code instructions for PrefectHQ/fastmcp, covering fastmcp development guidelines, required development workflow, repository structure, core mcp objects and development rules.
graphiti CLAUDE.md
Instructions for getzep/graphiti, covering claude.md, project overview, development commands, main development commands (run from project root) and install dependencies.
stagehand AGENTS.md
Instructions for browserbase/stagehand: Only a human may request changes to this file. Keep additions rare and limited to durable, repository-wide rules. -->.
graphiti AGENTS.md
Instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
autocontext CLAUDE.md
Instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.