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/codeswhat/portkey-admin-mcp/agents-mdgit clone --depth 1 https://github.com/CodesWhat/portkey-admin-mcpWhat 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 | $0.00071 | $0.00071 |
| Opus 5 | $0.00036 | $0.00036 |
| Sonnet 5 | $0.00014 | $0.00014 |
| Haiku 4.5 | $0.00007 | $0.00007 |
Grade A, and why
portkey-admin-mcp 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 2d 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
Agent Instructions
Notes for AI agents working in this repository.
Code review
This repo sets greptile.json to {"skipReview": "AUTOMATIC"} so Greptile only reviews a pull request on demand, when the second-opinion label is applied; CodeRabbit is the automatic reviewer for every PR.
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.
- 2d ago First seen · 8 lines · 71 tokens per session scan A f1b96ae0016c
portkey-admin-mcp AGENTS.md is an instructions file published in the GitHub repository CodesWhat/portkey-admin-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session, about $0.0004 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 2026-08-31.
Other instructions, from other repositories
unified-ai-system AGENTS.md
Instructions for happy520ai/unified-ai-system, covering repository guidance, ownership, language and module policy, public repository rules and safety.
ai-gateway AGENTS.md
Instructions for ferro-labs/ai-gateway, covering agents.md, project overview, current development snapshot, public-facing wording and build, test, and run commands.
litellm AGENTS.md
AGENTS.md instructions for BerriAI/litellm, a project described as: The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM].
litellm GEMINI.md
Gemini CLI instructions for BerriAI/litellm, a project described as: The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM].
gateway CLAUDE.md
Instructions for Portkey-AI/gateway, covering claude.md, project overview, development commands, core development and testing.
mcp-zenml CLAUDE.md
Instructions for zenml-io/mcp-zenml, covering claude.md, commands, testing and development, code quality and development workflow.