Borrowing it
Nothing to install: this file belongs to ajsai47/holyclaude. 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/ajsai47/holyclaude/main/CLAUDE.mdgit clone --depth 1 https://github.com/ajsai47/holyclaudeWrote 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/ajsai47/holyclaude/claude-md)<a href="https://agentmods.dev/instructions/ajsai47/holyclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/ajsai47/holyclaude/claude-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 | $0.01506 | $0.01506 |
| Opus 5 | $0.00753 | $0.00753 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
holyclaude 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 8d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HolyClaude
Six tools, one agent. HolyClaude combines persistent memory, structured workflows, virtual team review, headless browsing, autonomous experimentation, and Anthropic's official plugin collection into a single Claude Code plugin.
Architecture
Layer 6: Research /autoloop Autonomous experiment loops
Layer 5: Team /office-hours ... Virtual team review & deployment
Layer 4: Workflow /spec /plan ... Structured dev process
Layer 3: Plugins /feature-dev ... Anthropic official plugins (14)
Layer 2: Browser /browse Headless Chrome automation
Layer 1: Memory /mem-search ... Persistent cross-session memory
Layer 0: Claude Code Foundation runtime
Each layer builds on those below it. Memory persists context across sessions. Workflows structure your development process. The virtual team reviews your work. The browser lets you test and research. The experiment loop optimizes autonomously.
Integrated Flow
The full development cycle through all layers:
- Memory recall -- Session starts, claude-mem loads context from previous sessions
- Office hours --
/office-hoursto discuss approach with virtual team leads - Spec --
/specto write a detailed specification - Plan --
/planto break the spec into implementation steps - Build --
/subagent-devor/tddto implement with tests - Review --
/reviewfor pre-landing diff review by virtual specialists - QA --
/qafor comprehensive quality assurance - Ship --
/shipto create PR, push, and deploy - Memory persist -- Session ends, observations auto-saved for next time
You do not need to use every step for every task. Pick what fits.
Skill Reference
Memory Layer (claude-mem)
Auto-starts on session. Captures observations from tool use. Persists across sessions.
| Skill | When to Use |
|---|---|
/mem-search |
Find work from previous sessions |
/make-plan |
Create a plan with memory-informed context |
/do |
Execute a task with memory awareness |
/smart-explore |
Explore codebase with memory-guided heuristics |
/timeline-report |
View chronological activity around a point in time |
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.
- 8d ago First seen · 158 lines · 1,506 tokens per session scan A 173a2e1bee75
holyclaude CLAUDE.md is an instructions file published in the GitHub repository ajsai47/holyclaude (11 stars, last pushed 5mo ago), licensed MIT. It adds 1,506 tokens to every session, about $0.0075 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
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.