Borrowing it
Nothing to install: this file belongs to stefanhoelzl/codehydra. 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/stefanhoelzl/codehydra/main/AGENTS.mdgit clone --depth 1 https://github.com/stefanhoelzl/codehydraWrote 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/stefanhoelzl/codehydra/agents-md)<a href="https://agentmods.dev/instructions/stefanhoelzl/codehydra/agents-md"><img src="https://agentmods.dev/badge/instructions/stefanhoelzl/codehydra/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/stefanhoelzl/codehydra/agents-md"><img src="https://agentmods.dev/badge/instructions/stefanhoelzl/codehydra/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 | $0.02963 | $0.02963 |
| Opus 5.5 | $0.01185 | $0.01185 |
| Sonnet 5.5 | $0.00593 | $0.00593 |
| Haiku 4.5 | $0.00296 | $0.00296 |
Grade A, and why
codehydra AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `ElectronBuildInfo` → `execSync`: unpackaged only; reads the git branch synchronously at startup, before config registration derives the dev ports from it; `ProcessRunner` is async-only and does not exist yet. How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this repository. This file holds what every session needs; the rest loads on demand — see Where things live.
CRITICAL RULES
These rules MUST be followed. Violations require explicit user approval.
No Ignore Comments
NEVER add without explicit user approval:
// @ts-ignore,// @ts-expect-error,// eslint-disable*,anytype assertions- Modifications to
.eslintignore,.prettierignore
API/IPC Interface Changes
NEVER modify without explicit user approval:
- IPC channel names/signatures (
api:project:*,api:workspace:*) - Intent/event type definitions, operation interfaces
- Preload script exposed APIs, event names/payloads, shared types in
src/shared/
Why: IPC contracts affect main/renderer sync, type safety, and backwards compatibility.
New Boundary Interfaces
NEVER add without explicit user approval:
- New abstraction interfaces (
*Layer,*Client,*Provider) - New boundary types (I/O, network, filesystem, process abstractions)
- Entries to External System Access Rules table
Why: Architectural decisions with maintenance burden. Must follow established patterns.
External System Access Rules
All external access MUST use abstraction interfaces:
| External System | Required Interface | Forbidden Direct Access |
|---|---|---|
| Filesystem | FileSystemBoundary |
node:fs/promises |
| HTTP requests | HttpClient |
fetch() |
| Port operations | PortManager |
net module |
| Local sockets | LocalSocketClient |
net.createConnection |
| Process spawning | ProcessRunner |
execa |
| Agent operations | AgentProvider, AgentServerManager |
Direct agent SDK/client |
| OpenCode API | WireClient (1.x @opencode-ai/sdk, 2.x @opencode/client) |
Direct HTTP/SSE |
| Git operations | IGitClient |
simple-git |
| Electron Window | WindowBoundary |
BaseWindow |
| Electron View | ViewBoundary |
WebContentsView |
| Electron Session | SessionBoundary |
session |
| Electron IPC | ViewBoundary.send / onIpc |
ipcMain |
| Electron Dialog | DialogBoundary |
dialog |
| Electron Image | ImageBoundary |
nativeImage |
| Electron App | AppBoundary |
app |
| Electron Power | AppBoundary.allowPowerSaving |
powerSaveBlocker |
| Electron Menu | MenuBoundary |
Menu |
| Electron Notification | OsNotificationBoundary |
Notification |
| PostHog telemetry | PostHogBoundary |
posthog-node |
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.
- 4d ago First seen · 229 lines · 2,963 tokens per session scan A 17d2a5b408ca
codehydra AGENTS.md is an instructions file published in the GitHub repository stefanhoelzl/codehydra (20 stars, last pushed today), licensed MIT. It adds 2,963 tokens to every session, about $0.0119 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.