shotik: Instructions file for Codex

AGENTS.md

shotik AGENTS.md is an instructions file for Codex, OpenCode from gorka2354/shotik. It costs 942 tokens per session, scanned A, original, MIT.

Project instructions for coding agents working on Shotik, a Rust and Windows screenshot application with an integrated tool server. They describe the codebase, test environment, and safety rules for avoiding the user's real desktop and data.

In plain words
What is it for?
Use them when inspecting, changing, building, or testing the Shotik project.
Why use it?
They reduce the risk of tests opening windows, affecting the user's application, changing shared clipboard contents, or exposing private screen and audio data.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is gorka2354/shotik's own configuration. It tells Codex and OpenCode how to work on shotik 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 shotik configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gorka2354/shotik. 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/gorka2354/shotik/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/gorka2354/shotik

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 shotik AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gorka2354/shotik/agents-md/github.svg)](https://agentmods.dev/instructions/gorka2354/shotik/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gorka2354/shotik/agents-md"><img src="https://agentmods.dev/badge/instructions/gorka2354/shotik/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.

agentmods 80×15 button for shotik AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gorka2354/shotik/agents-md"><img src="https://agentmods.dev/badge/instructions/gorka2354/shotik/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 942 This file is loaded in full into every session.
When invoked 942 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00942 $0.00942
Opus 5.5 $0.00377 $0.00377
Sonnet 5.5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured today against content hash 9df45d04a17f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shotik 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 today.

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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shotik: instructions for coding agents

Shotik is an open-source Windows screenshot tool with a built-in MCP server, written in Rust (crates/). The Electron version it replaced stays readable at tag electron-final: comments and docs that mention src/... point there. When a behaviour is unclear, read that code, do not guess.

Read first: docs/rust/ARCHITECTURE.md, docs/rust/CONTRACT.md.

Hard rules

  1. Never touch the user's desktop. The user works at this machine while agents run.
    • No visible windows, no focus stealing, no global hotkey registration, no real clicks or keystrokes. Test instances run in ghost mode (SHOTIK_GHOST=1, windows at x+20000).
    • The clipboard is shared with the user: save and restore it around anything that writes to it.
    • Real screen pixels and real audio are private: never commit them, never write them outside a temporary directory, and delete that directory when done. Use test/fake-screen.png by default.
    • Never kill processes you did not start. Shotik.exe on this machine is the user's real app.
    • Never start the binary without --test and a private APPDATA: without them it opens the user's real profile, and it has no --version to stop it.
    • The one exception is test/live/, which takes over the desktop on purpose: only with the owner's agreement and on an idle machine. Ghost mode cannot see focus, DPI changes or native dialogs, so a change to any of those needs that check, or a plain statement that it did not get one.
  2. Stay inside your allowed paths. Each task names the files or crates it owns. If you need a change elsewhere, do not make it: describe it in your final summary. crates/shotik-core/src/ports.rs is shared: additive changes only, and name them in your summary.
  3. Done means verified. Report the exact command and its result. If something could not be verified, say so and why. Do not write "should work".
  4. Explicit errors. A silent fallback that carries on as if nothing happened is a bug. Every port returns a typed error; the caller decides what the user sees.
  5. Test the contract, not the implementation. Pure logic gets unit tests that survive a refactor.
  6. No secrets in code, docs, commits or logs. settings.json may contain a DeepL key. .env holds the update signing key, which decides what every installed copy will run: do not read or print it, and never copy it anywhere. Only installer/publish-release.js uses it (docs/rust/UPDATES.md).

Read the full file on GitHub · 61 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. today Changed · +2 lines · +54 tokens per session 9df45d04a17f
  2. yesterday First seen · 59 lines · 888 tokens per session scan A 37a1b672c31c

Subscribe to this mod's changes

shotik AGENTS.md is an instructions file published in the GitHub repository gorka2354/shotik (3 stars, last pushed yesterday), licensed MIT. It adds 942 tokens to every session, about $0.0038 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 2026-11-05.

Related

shotik AGENTS.md compared with instructions from other repositories

shotik AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
shotik AGENTS.mdgorka2354/shotikInstructions file3yesterdayMITA942Codex, OpenCode
vibetags com-example-config-AsyncTestConfig.instructions.mdPIsberg/vibetagsInstructions file25todayMITA82GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot