pin-it-public: Instructions file for Codex

AGENTS.md

pin-it-public AGENTS.md is an instructions file for Codex, OpenCode from johnnyzhoujz/pin-it-public. It costs 414 tokens per session, scanned A, original, MIT.

A set of working and testing instructions for the Pin It desktop app repository. It covers code checks, packaged-app testing, signing, and macOS permissions.

In plain words
What is it for?
Making changes to Pin It, running its checks, rebuilding the Mac app, and verifying Screen Recording permissions and the visible app.
Why use it?
It gives an agent the project-specific rules needed to avoid disturbing unrelated changes and to test the correct app build.

Instructions file for CodexOpenCode

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

This is johnnyzhoujz/pin-it-public's own configuration. It tells Codex and OpenCode how to work on pin-it-public 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 pin-it-public configures →

Reuse

Borrowing it

Nothing to install: this file belongs to johnnyzhoujz/pin-it-public. 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/johnnyzhoujz/pin-it-public/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/johnnyzhoujz/pin-it-public

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 pin-it-public AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/johnnyzhoujz/pin-it-public/agents-md"><img src="https://agentmods.dev/badge/instructions/johnnyzhoujz/pin-it-public/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 414 This file is loaded in full into every session.
When invoked 414 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 $0.00414 $0.00414
Opus 5 $0.00207 $0.00207
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00041 $0.00041

Measured 9d ago against content hash 6b6b8847020d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pin-it-public 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 9d 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 · 48 lines

What it actually says

Pin It repository guidance

Working practices

  • Use grep for local text searches.
  • Use the GitHub CLI (gh) for GitHub repository, issue, pull request, release, and workflow operations.
  • Preserve unrelated and uncommitted user changes.
  • Keep behavior changes, mechanical cleanup, generated assets, and release work in separate commits.
  • Run npm run check before publishing a code change.

Packaged-app testing

  • The local manual-test bundle is release/mac-arm64/Pin It.app.
  • Stop the visible app process before replacing a local package.
  • Remove the old bundle before running npm run pack:mac; do not layer a new app bundle over an old one.
  • Relaunch and verify the exact bundle path rather than relying on the app name, because duplicate Pin It.app bundles may exist.
  • Claude-managed or other MCP helper processes can include the same app binary path in their command line. Do not treat those helpers as proof that the visible UI process is still running.

Local packages are ad-hoc signed unless a valid Developer ID identity is available. A rebuild can change the code-signing requirement that macOS TCC associates with Screen Recording permission. If region capture repeatedly asks for permission after a rebuild, verify which app bundle is running and reset only Pin It's Screen Recording grant:

tccutil reset ScreenCapture xyz.justpinit.app

Do not change build.appId to work around a TCC problem. The durable release fix is stable Developer ID signing and notarization.

Use this only as a local integrity check:

codesign --verify --deep --strict --verbose=2 "release/mac-arm64/Pin It.app"

It does not prove Developer ID signing or notarization.

Pin data lives under the user's Electron app-data directory, not inside the app bundle, so replacing a packaged app should not remove saved pins or images.

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. 9d ago First seen · 48 lines · 414 tokens per session scan A 6b6b8847020d

Subscribe to this mod's changes

pin-it-public AGENTS.md is an instructions file published in the GitHub repository johnnyzhoujz/pin-it-public (4 stars, last pushed 6d ago), licensed MIT. It adds 414 tokens to every session, about $0.0021 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens