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/maorbril/clauder/claude-mdgit clone --depth 1 https://github.com/MaorBril/clauderWrote 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/maorbril/clauder/claude-md)<a href="https://agentmods.dev/instructions/maorbril/clauder/claude-md"><img src="https://agentmods.dev/badge/instructions/maorbril/clauder/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 | $0.00757 | $0.00757 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
clauder 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 4d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Clauder - Persistent Memory MCP
This project uses clauder for persistent memory across Claude Code sessions.
CRITICAL: Call get_context at Session Start
IMPORTANT: You MUST call mcp__clauder__get_context at the START of every session to load:
- Stored facts and decisions from previous sessions
- User preferences and coding style guidelines
- Unread messages from other Claude Code instances
This context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.
Available Tools
- mcp__clauder__remember: Store facts, decisions, or context
- mcp__clauder__recall: Search and retrieve stored facts
- mcp__clauder__forget: Delete a stored fact by ID (requires confirmation)
- mcp__clauder__get_context: Load all relevant context for this directory (also shows sibling instances)
- mcp__clauder__get_global_context: Load ALL facts across every directory/repository (use when you need context from other projects)
- mcp__clauder__list_instances: List other running Claude Code sessions (grouped by directory)
- mcp__clauder__send_message: Send messages to other instances (supports broadcast to directory)
- mcp__clauder__get_messages: Check for incoming messages
- mcp__clauder__rename_instance: Set or change THIS session's name on the fly (no restart) so other instances can discover and message it
Memory Management Tools
- mcp__clauder__compact_context: Review all facts with age/size metadata for cleanup (supports
global: truefor all directories) - mcp__clauder__compress_facts: Atomically replace old facts with consolidated ones (delete + add in one transaction)
- mcp__clauder__update_fact: Update an existing fact's content/tags in place (preserves ID and creation date)
- mcp__clauder__fact_stats: Get statistics about stored facts (counts, sizes, age, per-directory breakdown)
- mcp__clauder__purge_deleted: Permanently remove soft-deleted facts to reclaim space
- mcp__clauder__bulk_forget: Delete multiple facts by IDs
- mcp__clauder__bulk_remember: Store multiple facts in one call
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.
- 4d ago First seen · 50 lines · 757 tokens per session scan A a8f07ed3cda4
clauder CLAUDE.md is an instructions file published in the GitHub repository MaorBril/clauder (53 stars, last pushed 1mo ago), licensed MIT. It adds 757 tokens to every session, about $0.0038 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
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).