Borrowing it
Nothing to install: this file belongs to guillem/stallhunt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/guillem/stallhunt/main/AGENTS.mdgit clone --depth 1 https://github.com/guillem/stallhuntWrote 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.
[](https://agentmods.dev/instructions/guillem/stallhunt/agents-md)<a href="https://agentmods.dev/instructions/guillem/stallhunt/agents-md"><img src="https://agentmods.dev/badge/instructions/guillem/stallhunt/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/guillem/stallhunt/agents-md"><img src="https://agentmods.dev/badge/instructions/guillem/stallhunt/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01984 | $0.01984 |
| Opus 5.5 | $0.00794 | $0.00794 |
| Sonnet 5.5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00198 | $0.00198 |
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 2mo 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.
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:
- whether meaningful contention exists,
- which resource is constraining progress,
- which processes/services are being delayed,
- which processes/services are likely causing the contention,
- how much time is being lost,
- what evidence supports the diagnosis,
- 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:
README.mddocs/README.mddocs/product.mddocs/architecture.mddocs/status.md- relevant files under
docs/decisions/ - any domain-specific document relevant to the requested work
For implementation work, also read:
docs/data-model.mddocs/telemetry.mddocs/inference-engine.mddocs/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.
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.
- 2mo ago First seen · 354 lines · 1,984 tokens per session scan A 5542b5134553
stallhunt AGENTS.md is an instructions file published in the GitHub repository guillem/stallhunt (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,984 tokens to every session, about $0.0079 per session on Opus 5.5. 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.
stallhunt AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stallhunt AGENTS.mdguillem/stallhunt | Instructions file | 2 | 2mo ago | Apache-2.0 | A | 1,984 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |