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/christian-katzmann/app-it/agents-mdgit clone --depth 1 https://github.com/Christian-Katzmann/app-itWrote 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/christian-katzmann/app-it/agents-md)<a href="https://agentmods.dev/instructions/christian-katzmann/app-it/agents-md"><img src="https://agentmods.dev/badge/instructions/christian-katzmann/app-it/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 5.1 | $0.01158 | $0.01158 |
| Opus 5 | $0.00579 | $0.00579 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
app-it 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operating notes for AI agents (and humans) working on the app-it repo itself — not on a project that app-it is packaging. If you're here to use the skill, read the README and SKILL.md instead.
Safe first command
git status --short # see what's dirty before touching anything
Verify — the one command
./scripts/validate.sh
It checks manifest shape, shell syntax (bash -n), plist lint, a Swift typecheck of wrapper.swift, claude plugin validate (when the CLI is present), and guards against leaked local paths and unresolved template placeholders. CI runs the same script on macos-latest. Green here is the bar for every change.
What this repo is
Three sibling plugins, each packaged for two assistants (Claude Code + Codex). That's why some files look duplicated — they aren't:
app-it(macOS, proven, daily use) — runs a project's dev server behind a native window.plugins/app-it/skills/app-it/SKILL.md(+templates/).app-it-static(macOS, companion) — serves a finished build (no dev server).plugins/app-it-static/skills/app-it-static/SKILL.md(+templates/).app-it-windows(beta scaffold, maintainer wanted) — the Windows sibling.plugins/app-it-windows/skills/app-it-windows/SKILL.md.
Each plugin has Claude packaging (.claude-plugin/) and Codex packaging (.codex-plugin/ + the shared .agents/plugins/marketplace.json). A plugin's manifests carry the same version (the coupling is per-plugin, not across plugins). validate.sh asserts it; releases bump them together (see docs/RELEASE_CHECKLIST.md).
app-it-static reuses five app-it templates byte-for-byte — wrapper.swift, desktop-icons.sh, desktop-install.sh, info-plist-template.xml, placeholder-icon-gen.sh. Each plugin must be self-contained for marketplace install, so they're duplicated, but validate.sh diffs them and fails on drift. If you change launcher internals, edit app-it's copy and re-sync app-it-static's — never let them diverge.
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.
- 6d ago First seen · 53 lines · 1,158 tokens per session scan A e31c526aeb17
app-it AGENTS.md is an instructions file published in the GitHub repository Christian-Katzmann/app-it (217 stars, last pushed 1mo ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0058 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
starboard CLAUDE.md
Claude Code instructions for palamim/starboard, covering claude.md, commands, code style, architecture and non-obvious gotchas (not discoverable by reading the code).
mac-it-guy-pro AGENTS.md
AGENTS.md instructions for xiaolai/mac-it-guy-pro, covering working conventions for this repo, privacy discipline when testing against a real machine, english only, verification before release and which matcher a new guard rule should use.
moonproxy-desktop AGENTS.md
AGENTS.md instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.
cctop AGENTS.md
AGENTS.md instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
magi-workflow CLAUDE.md
Instructions for howar31/magi-workflow, covering what this is, slash commands, subagents, project state model and project document tiers.