stallhunt AGENTS.md

stallhunt AGENTS.md is an instructions file for Codex, OpenCode from guillem/stallhunt. It costs 1,984 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Stallhunt, a Linux-first command-line tool that finds system performance bottlenecks and explains which resources, processes, and services are involved.

In plain words
What is it for?
Use them when developing or investigating Stallhunt's performance diagnosis features.
Why use it?
They give coding agents the project's goals, operating rules, decisions, and current state so work can continue with the repository as its source of truth.

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/guillem/stallhunt/agents-md
Clone the repo
git clone --depth 1 https://github.com/guillem/stallhunt

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stallhunt AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/guillem/stallhunt/agents-md.svg)](https://agentmods.dev/instructions/guillem/stallhunt/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/guillem/stallhunt/agents-md"><img src="https://agentmods.dev/badge/instructions/guillem/stallhunt/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,984 This file is loaded in full into every session.
When invoked 1,984 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 $0.01984 $0.01984
Opus 5 $0.00992 $0.00992
Sonnet 5 $0.00397 $0.00397
Haiku 4.5 $0.00198 $0.00198

Measured 4d ago against content hash 5542b5134553, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stallhunt 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 4d 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 · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository is the source of truth for the Stallhunt project.

Mission

Build a Linux-first command-line tool that automatically identifies active system performance bottlenecks and explains:

  1. whether meaningful contention exists,
  2. which resource is constraining progress,
  3. which processes/services are being delayed,
  4. which processes/services are likely causing the contention,
  5. how much time is being lost,
  6. what evidence supports the diagnosis,
  7. how confident the tool is in each causal claim.

The project is not another top clone. Traditional monitors report resource consumption. Stallhunt should report lost progress and likely causes.

Product name: Stallhunt. Crate, package, and binary: stallhunt. See ADR-0012.

Operating principle

Treat Git as project memory.

A fresh clone on another computer must contain enough information for a competent coding agent or engineer to understand:

  • what the project is,
  • what has already been implemented,
  • what decisions have been made,
  • what remains,
  • what is currently broken,
  • what should be done next,
  • why the architecture looks the way it does.

Do not rely on chat history as durable project context.

Required reading order

Before making non-trivial changes, read:

  1. README.md
  2. docs/README.md
  3. docs/product.md
  4. docs/architecture.md
  5. docs/status.md
  6. relevant files under docs/decisions/
  7. any domain-specific document relevant to the requested work

For implementation work, also read:

  • docs/data-model.md
  • docs/telemetry.md
  • docs/inference-engine.md
  • docs/testing.md

Project constraints

Platform

  • Linux first.
  • Native Linux kernel interfaces are preferred over portability abstractions when they materially improve diagnosis.
  • Other operating systems are explicitly out of scope until the Linux implementation is useful and stable.

Language

  • Rust is the implementation language.
  • Prefer stable Rust unless an ADR explicitly approves nightly-only functionality.

Read the full file on GitHub · 354 lines

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. 4d ago First seen · 354 lines · 1,984 tokens per session scan A 5542b5134553

Subscribe to this mod's changes

stallhunt AGENTS.md is an instructions file published in the GitHub repository guillem/stallhunt (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,984 tokens to every session, about $0.0099 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens