agentmods.dev

kiwiki: Instructions file for Codex

AGENTS.md

kiwiki AGENTS.md is an instructions file for Codex, OpenCode from natorus87/kiwiki. It costs 1,485 tokens per session, scanned A, original, MIT.

A set of instructions for AI assistants working on the kiwiki project. It defines the project language rules, localization requirements, code conventions, and available helper agents.

In plain words
What is it for?
Use it when changing kiwiki’s user interface, accessibility text, browser messages, localization behavior, tests, or project documentation.
Why use it?
It reduces inconsistent translations and helps ensure that visible changes, browser messages, and tests support both German and English.

Instructions file for CodexOpenCode

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

This is natorus87/kiwiki's own configuration. It tells Codex and OpenCode how to work on kiwiki 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 kiwiki configures →

not rated 2repo changed 1mo ago A scan 1,485 tokens original MIT
View source ↗ natorus87/kiwiki
Reuse

Borrowing it

Nothing to install: this file belongs to natorus87/kiwiki. 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/natorus87/kiwiki/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/natorus87/kiwiki

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 kiwiki AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/natorus87/kiwiki/agents-md/github.svg)](https://agentmods.dev/instructions/natorus87/kiwiki/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/natorus87/kiwiki/agents-md"><img src="https://agentmods.dev/badge/instructions/natorus87/kiwiki/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 kiwiki AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/natorus87/kiwiki/agents-md"><img src="https://agentmods.dev/badge/instructions/natorus87/kiwiki/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,485 This file is loaded in full into every session.
When invoked 1,485 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 $0.01485 $0.01485
Opus 5.5 $0.00594 $0.00594
Sonnet 5.5 $0.00297 $0.00297
Haiku 4.5 $0.00148 $0.00148

Measured 1mo ago against content hash 4f8e14f29e54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kiwiki 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 1mo 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 · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Projekt-Anweisungen

Dieses Projekt nutzt eine modulare .claude/-Struktur. Halte diese Datei kurz – Details liegen in spezialisierten Agenten, Regeln und Skills.

Wichtig: Die Inhalte von .claude/ sind bewusst nicht versioniert (.gitignore). Ein frischer Klon hat sie nicht. Die Pfade unten sind der Soll-Zustand dieser Arbeitskopie, keine Garantie für andere Maschinen. Verlasse dich für repo-getragene Regeln auf diese Datei plus docs/, nicht auf .claude/.

Projekt-Kontext

  • Sprache: Deutsch (Kommentare & Doku), Code in Englisch
  • Produktoberfläche: Deutsch und Englisch (siehe verbindliche Lokalisierungsregel unten)
  • Architektur-Entscheidungen: @docs/architecture.md

Verbindliche Lokalisierungsregel

  • Jede neue oder geänderte sichtbare UI, Microcopy, ARIA-Beschriftung sowie dynamische Browsermeldung muss gleichzeitig auf Deutsch (de) und Englisch (en) vorliegen.
  • Keine neue Oberfläche darf mit fest verdrahteten Texten in nur einer Sprache abgeschlossen werden. Server-Templates und JavaScript-Zustände zählen gleichermaßen.
  • Die Sprachwahl muss semantisch über <html lang> abgebildet und für weitere Aufrufe gespeichert werden; ohne explizite Wahl dient Accept-Language als Fallback.
  • Neue UI-Funktionen benötigen mindestens je einen Test für Deutsch und Englisch.
  • Code-Bezeichner bleiben Englisch; Kommentare und technische Projektdokumentation bleiben Deutsch, sofern kein englisches Nutzerhandbuch betroffen ist.

Regeln (lokal, automatisch geladen via .claude/rules/)

Regeln in .claude/rules/ werden von Claude Code automatisch eingebunden:

  • Code-Stil (code-stil.md) — Formatierung, Benennung, Architektur
  • Test-Konventionen (testen.md) — Pflicht-Tests, Mocking, Ausführung
  • API-Design (api-konventionen.md) — nur via paths:; die Pfade dort zielen auf ein src/api/**-Layout, das kiwiki nicht hat. Für die FastAPI-Endpunkte in app/main.py gilt die Regel derzeit nicht automatisch — bei Bedarf paths: auf app/*.py anpassen
  • Workflow (workflow.md) — Context-Management, Planung, Sub-Agenten
  • Git (git-workflow.md) — Commit-Regeln, Branches, Push-Checks

Read the full file on GitHub · 109 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. 1mo ago Changed · +3 lines · +71 tokens per session 4f8e14f29e54
  2. 1mo ago Changed · +29 lines · +354 tokens per session e6ff093469f1
  3. 2mo ago First seen · 77 lines · 1,060 tokens per session scan A 251e7bf789af

Subscribe to this mod's changes

kiwiki AGENTS.md is an instructions file published in the GitHub repository natorus87/kiwiki (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,485 tokens to every session, about $0.0059 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 2026-08-31.

Localizationaidockerfastapiknowledge-basemarkdownmcp
Related

kiwiki AGENTS.md compared with instructions from other repositories

kiwiki AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kiwiki AGENTS.mdnatorus87/kiwikiInstructions file21mo agoMITA1,485Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot