Borrowing it
Nothing to install: this file belongs to StackOneHQ/stack-nudge. 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/StackOneHQ/stack-nudge/main/AGENTS.mdgit clone --depth 1 https://github.com/StackOneHQ/stack-nudgeWrote 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/stackonehq/stack-nudge/agents-md)<a href="https://agentmods.dev/instructions/stackonehq/stack-nudge/agents-md"><img src="https://agentmods.dev/badge/instructions/stackonehq/stack-nudge/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/stackonehq/stack-nudge/agents-md"><img src="https://agentmods.dev/badge/instructions/stackonehq/stack-nudge/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 | $0.02227 | $0.02227 |
| Opus 5.5 | $0.00891 | $0.00891 |
| Sonnet 5.5 | $0.00445 | $0.00445 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
stack-nudge 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repo. CLAUDE.md is a symlink to this file, so edit this one.
Keyboard navigation
The panel is meant to be driven entirely from the keyboard, and every page should feel like the same app. Before adding or changing a binding, check it against the rules below and against the page that already does the same thing. If a change has to break a rule, say why in a comment at the binding and add it to the known exceptions at the end of this section.
Key routing lives in panel/Panel.swift. panelHandlesGlobalKey owns the keys that mean the same thing everywhere, and panelHandlesKey has one branch per nav.mode for the rest. Selection and value state live on PanelNav.
Keys that mean the same thing on every page
These are handled once, in panelHandlesGlobalKey, which FloatingPanel.sendEvent calls before the first responder sees the key. That is what makes them work while a text field has focus too. Don't bind them in a page's branch, and don't give a text field its own handling for them (.onExitCommand and the like): it can never fire.
| Key | Meaning |
|---|---|
Esc |
In a text field, or while a shortcut is being recorded, cancel it (Esc with a modifier is recorded as the shortcut). Everywhere else, hide the panel: on every page, in every state, including setup, update and uninstall screens. Nothing else. |
⌘← / ⌘→ |
Previous / next top-level tab, without wrapping. While recording a hotkey they go to the recorder, which can't bind an arrow, so they do nothing. |
⌘, |
Open Settings, as in any Mac app. Works from a text field too; not while recording a hotkey, or on the setup and update screens. |
⌫ in an empty text field |
Cancel the field, as Esc does. |
Cancelling a field puts it back the way it was before you started and hands the keyboard back to its page. Recording a shortcut counts as editing one: cancelling keeps the old shortcut. A search, filter or new-entry field empties. A field holding a value goes back to that value: a rename keeps the old name, an extension config field its saved value. cancelField in Panel.swift does this per page, so a page that adds a text field adds its case there. The key that cancelled, or the combo a recording took, may still be held when the field lets go, so GlobalKeyRouter swallows its autorepeat until a fresh press.
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 Changed · +11 tokens per session bd1179b6e87b
- 8d ago Changed · +1 lines · +39 tokens per session 0d4e892cf926
- 9d ago Changed · +151 tokens per session 53bd697f86fe
- 10d ago First seen · 70 lines · 2,026 tokens per session scan A d1dff6ff6b0b
stack-nudge AGENTS.md is an instructions file published in the GitHub repository StackOneHQ/stack-nudge (24 stars, last pushed 2d ago), licensed MIT. It adds 2,227 tokens to every session, about $0.0089 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 2026-10-29.
stack-nudge AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stack-nudge AGENTS.mdStackOneHQ/stack-nudge | Instructions file | 24 | 2d ago | MIT | A | 2,227 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |