AniShelf: Instructions file for Codex

AGENTS.md

AniShelf AGENTS.md is an instructions file for Codex, OpenCode from samuelhe52/AniShelf. It costs 1,543 tokens per session, scanned A, original, Apache-2.0.

Developer notes for AniShelf, an iPhone app, covering routine build and test commands, simulator use, device checks, worktrees, and Swift file style.

In plain words
What is it for?
Use them when changing AniShelf, running its simulator tests, checking UI behavior, or creating files and worktrees.
Why use it?
They define the project’s preferred validation workflow and prevent agents from using device testing or special workflows without being asked.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; reads ~/.codex paths; mentions Codex.

This is samuelhe52/AniShelf's own configuration. It tells Codex and OpenCode how to work on AniShelf 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 AniShelf configures →

Reuse

Borrowing it

Nothing to install: this file belongs to samuelhe52/AniShelf. 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/samuelhe52/AniShelf/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/samuelhe52/AniShelf

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 AniShelf AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/samuelhe52/anishelf/agents-md/github.svg)](https://agentmods.dev/instructions/samuelhe52/anishelf/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/samuelhe52/anishelf/agents-md"><img src="https://agentmods.dev/badge/instructions/samuelhe52/anishelf/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 AniShelf AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/samuelhe52/anishelf/agents-md"><img src="https://agentmods.dev/badge/instructions/samuelhe52/anishelf/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,543 This file is loaded in full into every session.
When invoked 1,543 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 $0.01543 $0.01543
Opus 5.5 $0.00617 $0.00617
Sonnet 5.5 $0.00309 $0.00309
Haiku 4.5 $0.00154 $0.00154

Measured 6d ago against content hash 3facc823368c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AniShelf 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 6d 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AniShelf - Developer Notes

Workflow

  • Use Makefile targets for routine tasks (make help lists them).
  • Run make clean, make refresh-packages, or make format only when the task needs it or the user asks. make refresh-packages deletes Package.resolved, so dependencies can move to newer versions; make format rewrites the whole repository. Format only the files you touched with swift format -i <paths>.
  • Validate on the affected platform. For iOS, use make test-sim for broad simulator-based validation and make run-sim when validating runtime or UI behavior rather than relying only on make build. For native macOS, verify with make build-mac; launch with make run-mac only when the user asks. make run-mac loads an 800-entry fixture library by default, not the real library.
  • Physical-device targets (make run-device, make test, make test-app, make test-app-live-fetch) run only when the user explicitly asks. If a check needs a device, explain why and ask.
  • If the user asks to perform a change in a new worktree, create that worktree under .worktrees/ in the repository root.
  • Use the write-ai-doc skill for substantial features and decision-shaping fixes, as defined in docs-ai/workflow.md.

Code Style

  • When creating new Swift source files, include the standard Xcode file comment header. Attribute authorship to the agent (OpenAI Codex or Claude Code) on behalf of Samuel He, and use the real creation date in YYYY/M/D format:
    //
    //  FileName.swift
    //  AniShelf
    //
    //  Created by <agent> on behalf of Samuel He on YYYY/M/D.
    //
    
    Omit this header only when the user explicitly requests it.
  • Give scrollable content under a navigation bar (Form, List, ScrollView, including each step of a multi-step sheet) .preferredNavigationBarScrollEdgeEffect(), so it follows the soft-edges setting, followed by .navigationTitle(...), .inlineNavigationTitle(), and .toolbar. In sheet toolbars, put a dismiss button at .cancellationAction with SheetCloseLabel, and other buttons at .sheetLeading/.sheetTrailing, never at raw .topBar* placements, which break the Mac's sheet bar.
  • Pass plain string literals to SwiftUI APIs that already take a LocalizedStringKey (Text, Button, Label, .help, and similar); do not wrap them in LocalizedStringResource. Use LocalizedStringResource for user-facing strings held in properties, models, or enums, or passed to APIs that do not localize literals.

Read the full file on GitHub · 56 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. 6d ago Changed · +1 lines · +152 tokens per session 3facc823368c
  2. 13d ago Changed · -9 lines · +15 tokens per session 78bc5e914864
  3. 22d ago Changed · +18 tokens per session c91f9e9164e1
  4. 23d ago Changed · +1 lines · +6 tokens per session cd2b0f3df0ca
  5. 29d ago Changed · +5 lines · +261 tokens per session 2557d43bb36e
  6. 1mo ago Changed · -46 tokens per session a5c46a933928
  7. 1mo ago Changed · +4 lines · +50 tokens per session 6809a93bd147
  8. 2mo ago Changed · +4 tokens per session 7a610e2c78a4
  9. 2mo ago First seen · 54 lines · 1,083 tokens per session scan A 99b7b8345c25

Subscribe to this mod's changes

AniShelf AGENTS.md is an instructions file published in the GitHub repository samuelhe52/AniShelf (143 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,543 tokens to every session, about $0.0062 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 2026-08-30.

Related

AniShelf AGENTS.md compared with instructions from other repositories

AniShelf AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
AniShelf AGENTS.mdsamuelhe52/AniShelfInstructions file1433d agoApache-2.0A1,543Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode