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/marko-php/marko/claude-mdgit clone --depth 1 https://github.com/marko-php/markoWhat 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 | $0.00865 | $0.00865 |
| Opus 5 | $0.00432 | $0.00432 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
marko CLAUDE.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 2d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marko Framework
Marko is a modular PHP 8.5+ framework combining Magento's extensibility with Laravel's developer experience.
Core Principles
- Loud errors - No silent failures, helpful messages
- Explicit over implicit - No magic, everything discoverable
- Pragmatically opinionated - Guide toward better patterns, grounded in real-world needs
- True modularity - Interface/implementation split, clean boundaries
- No pseudo-functionality - Don't build fake features to demonstrate concepts; only build real functionality when core supports it. If there's nothing meaningful to build, build nothing.
Commands
# Run tests (fast — excludes slow destructive integration tests)
composer test
# Run all tests including destructive integration tests
composer test:all
# Run with coverage
./vendor/bin/pest -c phpunit.xml --parallel --exclude-group=integration-destructive --coverage --min=80
# Lint (check)
./vendor/bin/phpcs
# Lint (fix)
./vendor/bin/php-cs-fixer fix
# Static analysis — NOT part of composer test; must be zero errors
composer phpstan
# Everything the CI gate runs (tests + lint + static analysis)
composer ci
Every PR is gated by the CI workflow on Tests, Lint, and Static analysis. A red check blocks the merge; develop never carries a failing test, lint error, or PHPStan error.
Key Conventions
- Branch naming - all branches use
feature/{name}format, regardless of change type (fix, feature, refactor, docs, etc.). Never usefix/,chore/, or other prefixes - No hardcoded versions in composer.json - never add
"version"to package composer.json files; let Composer infer from the branch - Constructor property promotion - always use it
- Strict types - every file needs
declare(strict_types=1) - No magic methods - be explicit
- No final classes - blocks Preferences (extensibility)
- readonly - use when appropriate for immutability, not as blanket rule
- Type declarations - required on all parameters, returns, properties
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.
- 2d ago First seen · 87 lines · 865 tokens per session scan A 9894ef79a420
marko CLAUDE.md is an instructions file published in the GitHub repository marko-php/marko (393 stars, last pushed 3d ago), licensed MIT. It adds 865 tokens to every session, about $0.0043 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
zolinga copilot-instructions.md
Copilot instructions for webdevelopers-eu/zolinga, covering legacy note, fundamentals of zolinga development, basics, web components and translations.
catch-admin AGENTS.md
Instructions for JaguarJack/catch-admin, covering catchadmin v5 - ai agent guidelines, role, 规则, 技术栈 and project 目录说明.
instructor-php AGENTS.md
Instructions for cognesy/instructor-php, covering key reference files, monorepo root, individual subpackages, code style and agents package style.
FreshRSS css.instructions.md
Instructions for FreshRSS/FreshRSS, covering css files and right-to-left css files.
freek.dev CLAUDE.md
Claude Code instructions for spatie/freek.dev, covering laravel boost guidelines, foundational context, skills activation, conventions and verification scripts.
woocommerce AGENTS.md
AGENTS.md instructions for woocommerce/woocommerce, covering woocommerce monorepo - ai agents documentation, project overview, navigation guide, which documentation to use? and available skills.