Borrowing it
Nothing to install: this file belongs to ShaheerKhawaja/ProductionOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ShaheerKhawaja/ProductionOS/main/CLAUDE.mdgit clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOSWrote 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/shaheerkhawaja/productionos/claude-md)<a href="https://agentmods.dev/instructions/shaheerkhawaja/productionos/claude-md"><img src="https://agentmods.dev/badge/instructions/shaheerkhawaja/productionos/claude-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.
<a href="https://agentmods.dev/instructions/shaheerkhawaja/productionos/claude-md"><img src="https://agentmods.dev/badge/instructions/shaheerkhawaja/productionos/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04470 | $0.04470 |
| Opus 5 | $0.02235 | $0.02235 |
| Sonnet 5 | $0.00894 | $0.00894 |
| Haiku 4.5 | $0.00447 | $0.00447 |
Grade A, and why
ProductionOS 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 10d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProductionOS 2.0.0-beta.1 — 10 Composites
80-agent AI engineering OS with 41 commands, 65 skills (14 composites), 15 lifecycle hooks, and 10 composite entry points. Project-aware context switching. Self-learning telemetry. Built for solo founders shipping multiple products.
The rule: Never browse the full skill list. Use the 10 composites. Each routes to the best sub-skill for your context. See ~/.claude/skills/SKILL-ROUTER.md.
Capabilities
- 51 skills (34 hand-crafted dense runbooks + 17 auto-generated wrappers)
- 80 agents with YAML frontmatter (model routing, tool constraints, stakes classification)
- 15 hooks across 4 lifecycle events (SessionStart, PreToolUse, PostToolUse, Stop)
- 10 CLI tools (pos-init, pos-config, pos-analytics, pos-sync, pos-timeline-log, etc.)
- Obsidian vault integration — ~/SecondBrain/ for session persistence (configurable path)
- Research pipeline — deep-research (8-phase) with citation verification
- Marketing/SEO/Ads skills available via installed external plugins (gstack, everything-claude-code)
Core Systems
Self-Evaluation
- Self-Eval Protocol — 7 questions after every agent action (templates/SELF-EVAL-PROTOCOL.md)
- Score Gating — >= 8.0 is PASS. 6.0-7.9 triggers self-heal (max 3 loops). < 6.0 blocks and escalates.
- Eval Gate Hook — Runs periodically via hooks/eval-gate.sh (frequency configurable)
/self-evalcommand — Standalone evaluation of last output, session, or git diff
Design & UX
/designer-upgrade— Full UI/UX redesign: audit → design system → interactive HTML mockups → browser annotation → implementation plan/ux-genie— User stories from UI guidelines, journey mapping, friction analysis, agent dispatch- Mockup Generator — Self-contained HTML mockups with annotation overlay, dark mode, responsive preview, side-by-side comparison
- Design System Architect — Token system creation from codebase analysis
Session Context Management
- Progressive context loading — L0 (always) / L1 (on demand) / L2 (when referenced)
- Context rot detection — Monitors for repeated work, contradictions, quality drift
- Automatic compression — Triggers at 60% context usage, emergency at 80%
- Cross-session instinct transfer — Patterns with confidence > 0.8 persist globally
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.
- 10d ago First seen · 330 lines · 4,470 tokens per session scan A 02b8f32d6cd7
ProductionOS CLAUDE.md is an instructions file published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 4,470 tokens to every session, about $0.0224 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 2026-08-31.
Other instructions, from other repositories
ai-agent-rules-generator ui-design.instructions.md
Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.