planchette AGENTS.md

planchette AGENTS.md is an instructions file for Codex, OpenCode from shahriarshm/planchette. It costs 647 tokens per session, scanned A, original, MIT.

A set of instructions for using planchette, a command-line tool that lets an agent capture and control a computer window. It explains setup, window selection, screenshots, and the repeated observe-and-act workflow.

In plain words
What is it for?
Selecting a target window, capturing screenshots, and carrying out click or other documented actions based on what appears on screen.
Why use it?
It gives the agent rules for interacting with graphical applications safely and consistently. It also documents operating-system permissions and limitations such as Linux support being limited to X11.

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

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 planchette AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shahriarshm/planchette/agents-md.svg)](https://agentmods.dev/instructions/shahriarshm/planchette/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/shahriarshm/planchette/agents-md"><img src="https://agentmods.dev/badge/instructions/shahriarshm/planchette/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 647 This file is loaded in full into every session.
When invoked 647 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 $0.00647 $0.00647
Opus 5 $0.00324 $0.00324
Sonnet 5 $0.00129 $0.00129
Haiku 4.5 $0.00065 $0.00065

Measured 4d ago against content hash 0da589b8c912, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planchette 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Driving a window with the planchette CLI

You (the agent) are the control loop: capture the window, look at the screenshot, decide one action, run it, look again.

Setup

  • planchette must be on PATH (uv tool install . from this repo).
  • macOS: the terminal app needs Screen Recording + Accessibility permission (System Settings → Privacy & Security), else captures are black and input does nothing.
  • Windows: no special permission. Linux: X11 only (Wayland unsupported).

Selecting a window

  • Interactive (macOS): planchette pick — blocks until the user hovers and clicks a window under the overlay; allow a generous timeout (120s).
  • Headless / any OS: planchette pick --list to see candidates, then planchette pick --name "Telegram" (case-insensitive substring of app name or title; frontmost match wins).
  • planchette agent is the human-facing hotkey panel (it spawns its own agent session) — as an agent, never run it; use pick.

The loop

  1. planchette capture → prints PATH WIDTHxHEIGHT. View that PNG. All coordinates below are pixels in this image, origin top-left.
  2. One action:
    • planchette click X Y (--double for double-click, --right for context menu)
    • planchette drag X1 Y1 X2 Y2 (select text, move sliders, drag & drop)
    • planchette move X Y
    • planchette type "text" (types into the selected window — click the field first)
    • planchette key "cmd+t" (cmd/ctrl/alt/shift + key; --repeat N to press N times)
    • planchette scroll X Y up|down [lines]
  3. Re-capture and look again. Repeat until done.

Text too small to read? planchette capture --crop X Y W H saves a native-res zoom of that region (coords in last-capture pixels). It's a magnifier only — keep computing click coordinates in the full capture's space.

Rules

  • On macOS input goes to the selected window's process in the background — the user keeps their focus and cursor and can keep chatting while you drive. On Windows/Linux input follows real focus: warn the user not to touch anything.
  • Never act blind: one action per capture, always look before the next.
  • If actions have no visible effect in the next capture, planchette raise the window and retry once.
  • error: no window selected / no capture yet → run the missing precondition and retry. window is gone → re-run pick.
  • If the window falls behind another, planchette raise.
  • Stop and ask rather than guess or do anything destructive.

Read the full file on GitHub · 53 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 · 53 lines · 647 tokens per session scan A 0da589b8c912

Subscribe to this mod's changes

planchette AGENTS.md is an instructions file published in the GitHub repository shahriarshm/planchette (0 stars, last pushed 2mo ago), licensed MIT. It adds 647 tokens to every session, about $0.0032 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.