agentmods.dev

agentsd: Instructions file for Claude Code

CLAUDE.md

agentsd CLAUDE.md is an instructions file for Claude Code from paultyng/agentsd. It costs 447 tokens per session, scanned B, original, MIT.

Project instructions for agentsd, a Stream Deck plugin that coordinates local AI-agent sessions through Claude Code HTTP hooks. They describe its npm build commands, architecture, and session state machine.

In plain words
What is it for?
Use them when building, testing, linking, debugging, or changing agentsd, especially work involving SessionManager, HTTP hooks, Stream Deck controls, or session transitions.
Why use it?
They give coding agents the repository's required commands and explain how hook requests become Stream Deck updates, including permission and elicitation states.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is paultyng/agentsd's own configuration. It tells Claude Code how to work on agentsd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentsd configures →

not rated 11repo 2mo ago B scan 447 tokens original MIT
View source ↗ paultyng/agentsd
Reuse

Borrowing it

Nothing to install: this file belongs to paultyng/agentsd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/paultyng/agentsd/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/paultyng/agentsd

Made for: Claude Code.

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 agentsd CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/paultyng/agentsd/claude-md/github.svg)](https://agentmods.dev/instructions/paultyng/agentsd/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/paultyng/agentsd/claude-md"><img src="https://agentmods.dev/badge/instructions/paultyng/agentsd/claude-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.

agentmods 80×15 button for agentsd CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/paultyng/agentsd/claude-md"><img src="https://agentmods.dev/badge/instructions/paultyng/agentsd/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 447 This file is loaded in full into every session.
When invoked 447 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00447 $0.00447
Opus 5.5 $0.00179 $0.00179
Sonnet 5.5 $0.00089 $0.00089
Haiku 4.5 $0.00045 $0.00045

Measured 2mo ago against content hash b8f0439f0add, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agentsd CLAUDE.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `npm run hooks:install` / `npm run hooks:uninstall` — manage Claude Code HTTP hooks in `~/.claude/settings.json`
CLAUDE.md · 37 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

agentsd — a Stream Deck plugin for orchestrating local AI agent usage. Early stages.

Build & Test

Use npm scripts only — no Taskfile or Makefile.

  • npm run build — rollup build → com.paultyng.agentsd.sdPlugin/bin/plugin.js
  • npm run watch — rollup watch mode
  • npm run dev — Stream Deck dev mode
  • npm run link / npm run unlink — link/unlink plugin in Stream Deck
  • npm run hooks:install / npm run hooks:uninstall — manage Claude Code HTTP hooks in ~/.claude/settings.json
  • npm run debug:hooks — interactive hook debug script

Architecture

Claude Code HTTP hooks → Plugin HTTP server (127.0.0.1:9200) → SessionManager → Stream Deck button/dial updates. No bridge daemon, no PTY parsing. PermissionRequest hooks hold HTTP response open (120s timeout) for approve/deny from hardware buttons.

State machine

Sessions move through 5 states: DISCONNECTED → IDLE → PROCESSING → AWAITING_PERMISSION / AWAITING_ELICITATION. Auto-created sessions (missed SessionStart) start as IDLE. Current-state guards prevent nonsensical transitions (e.g. tool events from DISCONNECTED). PostToolUse intentionally stays in PROCESSING — Stop moves to IDLE.

Key behaviors

  • Auto-foreground: Elicitation and PermissionRequest events bring the session to the active slot.
  • Stale pruning: Sessions with no activity for 60s are pruned (PRUNE_INTERVAL_MS = 60s check).
  • Permission timeout: 120s (PERMISSION_TIMEOUT_MS). Sends explicit deny on timeout.
  • Action DI pattern: A single setManager() call in plugin.ts wires the SessionManager into all ManagedAction subclasses via a shared module-level reference in actions/base.ts.
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. 2mo ago First seen · 37 lines · 447 tokens per session scan B b8f0439f0add

Subscribe to this mod's changes

agentsd CLAUDE.md is an instructions file published in the GitHub repository paultyng/agentsd (11 stars, last pushed 2mo ago), licensed MIT. It adds 447 tokens to every session, about $0.0018 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Codeai-agentsstream-deck-pluginstreamdeck
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 · 9,715 tokens

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.

vercel/next.js · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens

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.

denoland/deno · 3,077 tokens