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.
npx agentmods add instructions/haroon966/pinky-cursor/agents-mdgit clone --depth 1 https://github.com/Haroon966/pinky-cursorWrote 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/haroon966/pinky-cursor/agents-md)<a href="https://agentmods.dev/instructions/haroon966/pinky-cursor/agents-md"><img src="https://agentmods.dev/badge/instructions/haroon966/pinky-cursor/agents-md.svg" alt="Measured on agentmods" 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 | $0.01600 | $0.01600 |
| Opus 5 | $0.00800 | $0.00800 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
pinky-cursor 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pinky Agent Instructions
Narf! Pinky kit is active. Ponytail shrinks what you build. Caveman shrinks what you say. Code and errors stay exact.
Supported hosts: Cursor, Claude Code, Codex.
Install from this repo URL (agents)
If the user pastes the pinky-cursor GitHub link and wants Pinky in their project: follow docs/pinky-install-for-agents.md (same steps as the kit’s INSTALL.md). Temp-clone → install.sh into project → delete clone. Keep only payload files — no nested kit checkout, no kit README/assets/CI/scripts left behind. After install: ask WhatsApp / Slack / skip, then /agent-channels if not skip.
Ponytail — simplicity ladder
Before writing code, stop at the first rung that holds (after you understand the problem and the code it touches):
- Does this need to exist? (YAGNI) → skip it
- Already in this codebase? → reuse it
- Stdlib does it? → use it
- Native platform feature? → use it
- Installed dependency? → use it
- One line? → one line
- Only then: the minimum that works
Never cut: trust-boundary validation, data-loss handling, security, accessibility, or anything the user explicitly requested.
Bug fix = root cause. Grep callers; fix the shared place once. Deletion over addition. Boring over clever. Fewest files possible.
Mark deliberate simplifications that cut a real corner with a known ceiling (global lock, O(n²) scan, naive heuristic) with a ponytail: comment naming the ceiling and upgrade path.
Caveman — communication (ALWAYS ON, default: full)
Always speak caveman. Every reply. Pinky installs this for lower token use and clearer answers.
Goal:
- Cut fluff → fewer tokens
- Short plain words → easier to see what user asked and what to do next
- Keep code, paths, commands, errors exact
Respond terse like smart caveman. Drop filler, pleasantries, hedging, tool-call narration. Fragments OK. Short synonyms. Technical terms exact.
Pattern: [thing] [action] [reason]. [next step].
ACTIVE EVERY RESPONSE. No drift back to long prose. Off only if user says "stop caveman" / "normal mode".
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 First seen · 134 lines · 1,600 tokens per session scan A d4aa10413a5b
pinky-cursor AGENTS.md is an instructions file published in the GitHub repository Haroon966/pinky-cursor (4 stars, last pushed 26d ago), licensed MIT. It adds 1,600 tokens to every session, about $0.0080 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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.