Borrowing it
Nothing to install: this file belongs to ostapondo/Plonk. 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/ostapondo/Plonk/main/AGENTS.mdgit clone --depth 1 https://github.com/ostapondo/PlonkWrote 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/ostapondo/plonk/agents-md)<a href="https://agentmods.dev/instructions/ostapondo/plonk/agents-md"><img src="https://agentmods.dev/badge/instructions/ostapondo/plonk/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/ostapondo/plonk/agents-md"><img src="https://agentmods.dev/badge/instructions/ostapondo/plonk/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 | $0.03557 | $0.03557 |
| Opus 5.5 | $0.01423 | $0.01423 |
| Sonnet 5.5 | $0.00711 | $0.00711 |
| Haiku 4.5 | $0.00356 | $0.00356 |
Grade A, and why
Plonk 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s 127.0.0.1:43917/ping # smoke test while the app is running How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent rules
Rules for AI agents working in this repo.
Layout
App/— Swift package, the menu bar app. One type per file, files stay under ~300 lines.mcp/— TypeScript MCP server:src/server.tscompiled todist/vianpm run build. Keep it a thin proxy; logic belongs in the app. Tests aremcp/test/*.test.js, run againstdist/on the Node test runner with no extra dependencies. Tool description rules are inmcp/AGENTS.md.scripts/build.sh— the only build entry point.
Inside App/Sources/plonk/, the pieces that are easy to get lost in:
Routerowns the route table and nothing else: every case is one line to the module that handles it, in aRouter+*file of its own.AppDelegate.swiftis the list of what the app is made of and the order it comes up in, and nothing else. Every module's wiring lives in anAppDelegate+<Module>.swiftbeside it, which is why none of those stored properties is private: Swift only lets an extension in the same file see that. New behavior goes in the module's file, or in a new one.ConfigStoreis the only way a setting is written.updateclamps and saves it, thendidMutatefires andAppDelegate.applyConfighands the whole config to every manager. Nothing pushes a single field at a manager itself.Inkholds the surfaces, the radius and the accent gradient every page draws with, andSettingRowsthe rows a settings card is made of. Pages compose those instead of spelling out colours.Resources/en.lproj/Localizable.stringsholds every word the user reads, and theStrings+*.swiftfiles declare the keys that reach it. Views hold keys, never sentences — see "Text" below.AppActionsis what the UI can ask the app to do: commands, not settings. A setting needs nothing there —update(\.field, to:)writes any field ofConfig.AppModelholds that config plus the state config cannot answer: what a manager is doing now, what macOS has granted, what is on screen. Views never reach past it.ScreenIdentityturns a screen index into the keys config is stored under.WindowAccessholds every Accessibility call that reads or moves a window, andWindowManageris its only caller: one decides where a window goes, the other is how it gets there. A window that moves withoutWindowManager.placeseeing it announces nothing. Two other surfaces talk to AX directly and are not behind it —ShortcutGuidewalks another app's menu bar andNewWindowWatchersubscribes to window-opened notifications. Anything about a window's frame belongs inWindowAccess; those two do not.
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 · 249 lines · 3,557 tokens per session scan A 43b3a05fe77f
Plonk AGENTS.md is an instructions file published in the GitHub repository ostapondo/Plonk (17 stars, last pushed 18d ago), licensed MIT. It adds 3,557 tokens to every session, about $0.0142 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Plonk AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Plonk AGENTS.mdostapondo/Plonk | Instructions file | 17 | 18d ago | MIT | A | 3,557 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |