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/atheurer/agentic-perf/agents-mdgit clone --depth 1 https://github.com/atheurer/agentic-perfWhat 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 | $0.03008 | $0.03008 |
| Opus 5 | $0.01504 | $0.01504 |
| Sonnet 5 | $0.00602 | $0.00602 |
| Haiku 4.5 | $0.00301 | $0.00301 |
Grade B, and why
agentic-perf AGENTS.md scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
themselves run as root over SSH with no additional confinement. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sleep 30 && curl http://localhost:8090/... How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentic-perf — AI Agent Guidelines
Project Overview
Multi-agent system for autonomous performance testing. Engineers submit natural-language requests; specialized AI agents triage, acquire hardware, install tooling, execute benchmarks, and deliver structured analysis.
Stack: Python 3.12+, FastAPI, asyncio, MCP, Pydantic, httpx. License: Apache 2.0.
Key File Paths
| Path | Purpose |
|---|---|
agents/base.py |
AgentBase — LLM loop, tool dispatch, state store client |
agents/{name}/agent.py |
Agent implementation (extends AgentBase) |
agents/{name}/prompts.py |
System prompt for the agent |
agents/{name}/server.py |
FastMCP tool server (runtime MCP subprocess) |
agents/introspection/agent.py |
Continuous passive observer (not AgentBase) |
agents/fleet/agent.py |
Fleet coordinator — deterministic iteration lifecycle (not AgentBase) |
agents/image_builder/agent.py |
Custom image builds via pluggable providers (not AgentBase) |
agents/mcp_client.py |
MCP client for multi-server tool routing |
orchestrator/dispatcher.py |
Status → agent mapping, dispatch logic |
orchestrator/main.py |
Poll loop, provider initialization |
state_store/models.py |
Ticket model, state machine, valid transitions |
state_store/store.py |
In-memory ticket store with transition enforcement |
providers/llm/ |
LLM providers (Claude, OpenAI-compat, mock) |
providers/skills/ |
Benchmark harness skill providers |
providers/resource/ |
Hardware resource providers (QUADS, AWS, PSAP) |
providers/events.py |
EventBus — audit trail (JSONL per ticket) |
providers/ssh.py |
Async SSH executor |
skills/ |
Per-harness docs read by agents at runtime |
tests/conftest.py |
Test fixtures: MockSkillProvider, MockSSHExecutor |
Running Services
Interactive (foreground)
./start.sh # state store (background) + orchestrator (foreground)
# Ctrl+C stops both
Background (for AI agents and scripted testing)
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 · 301 lines · 3,008 tokens per session scan B 826714de0b2b
agentic-perf AGENTS.md is an instructions file published in the GitHub repository atheurer/agentic-perf (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,008 tokens to every session, about $0.0150 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.