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/samuelhe52/anishelf/agents-mdgit clone --depth 1 https://github.com/samuelhe52/AniShelfWrote 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/samuelhe52/anishelf/agents-md)<a href="https://agentmods.dev/instructions/samuelhe52/anishelf/agents-md"><img src="https://agentmods.dev/badge/instructions/samuelhe52/anishelf/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 | $0.01083 | $0.01083 |
| Opus 5 | $0.00541 | $0.00541 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00108 | $0.00108 |
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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AniShelf - Developer Notes
Workflow
- Use the Makefile for routine tasks:
make clean,make refresh-packages,make format,make lint,make build,make test-sim, andmake run-sim. - Use
make test-simfor broad simulator-based validation. Usemake run-simwhen validating app runtime or UI behavior, unless the user explicitly asks for device-based verification. - Use
make run-devicefor build, install, and launch on a connected iPhone only when the user explicitly asks for device-based verification. - Prefer the smallest relevant build or test command before broad verification.
- If the user asks to perform a change in a new worktree, create that worktree under ../AniShelf-worktrees/.
- Do not use any of the
openspecworkflows unless the user explicitly requests it.
Code Style
- When creating new source files, include the standard Xcode file comment header. Use the format below, attributing authorship to the agent (OpenAI Codex Or Claude Code) on behalf of the user (replace
<username>with the actual GitHub username if known, otherwise use the user's name; use the real creation date inYYYY/M/Dformat):
Omit this header only when the user explicitly requests it.// // FileName.swift // AniShelf // // Created by <agent> on behalf of <username> on YYYY/M/D. // - Keep edits aligned with existing project style.
- Use
LocalizedStringResourcewhenever possible for user-facing SwiftUI strings, including labels, helper text, and accessibility copy.
Testing
- Unit tests live in
MyAnimeList/Tests/andDataProvider/Tests/. - Run the smallest relevant test target first, then use
make test-simwhen broad validation is warranted. Usemake testonly when the user explicitly asks for physical-device testing or there is a specific device-only reason. - When developing new features or adding tests, run only the relevant tests first. For app tests, pass one or more whitespace-separated Xcode test identifiers with
APP_TEST_ONLY, for examplemake test-app-sim APP_TEST_ONLY='MyAnimeListTests/LibraryMetadataRefreshTests'ormake test-app-sim APP_TEST_ONLY='MyAnimeListTests/LibraryExportManagerTests MyAnimeListTests/LibraryBackupRestoreTests'. For DataProvider package tests, use Swift Testing's native filter syntax, for examplemake test-dataprovider DATAPROVIDER_TEST_FILTER='LibrarySyncTests'ormake test-dataprovider DATAPROVIDER_TEST_FILTER='LibrarySyncTests|MigrationTests'. Only run the full suite when there is a good reason. - Do not create excessive or redundant tests. Add only the smallest set that protects distinct behavior, prefer extending existing tests, and avoid duplicating coverage across layers. Simple wiring, copy, or layout changes may need no new tests.
- If a simulator is already booted, use it for install/testing as appropriate. For changes affecting app runtime or UI behavior, prefer
make run-simover relying only onmake build. Do not boot a simulator without explicit user permission, even when tests require one.
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.
- 5d ago First seen · 54 lines · 1,083 tokens per session scan A 99b7b8345c25
AniShelf AGENTS.md is an instructions file published in the GitHub repository samuelhe52/AniShelf (132 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,083 tokens to every session, about $0.0054 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 2026-08-30.
Other instructions, from other repositories
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.
SwiftUIShaders AGENTS.md
Instructions for krispuckett/SwiftUIShaders, covering agents.md: architecture for coding agents, what this package is, how swiftui metal shader effects work (the mental model), how to add a new shader and how to modify an existing shader.
swiftui-native-component-design-skill AGENTS.md
Instructions for alexanderwe/swiftui-native-component-design-skill, covering agent guidelines for swiftui native component design skill, core principles, 1. component api design only, 2. no architectural mandates and 3. templates are adaptable, not literal.
everything-claude-code-mobile copilot-instructions.md
Copilot instructions for ahmed3elshaer/everything-claude-code-mobile: Use this repository's mobile guidance for Android, iOS, and Kotlin Multiplatform work.
Pepper CLAUDE.md
Instructions for skwallace36/Pepper, covering pepper, mcp tools, conventions, writing docs and work tracking.