Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. 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/zkysar1/Claude-Mind/main/CLAUDE.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/claude-md)<a href="https://agentmods.dev/instructions/zkysar1/claude-mind/claude-md"><img src="https://agentmods.dev/badge/instructions/zkysar1/claude-mind/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 | $0.11399 | $0.11399 |
| Opus 5 | $0.05699 | $0.05699 |
| Sonnet 5 | $0.02280 | $0.02280 |
| Haiku 4.5 | $0.01140 | $0.01140 |
Grade B, and why
Claude-Mind CLAUDE.md scanned grade B with 1 finding 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `.claude/settings.local.json`, `core/scripts/settings-structural-validator.{py,sh}` | **CONSTITUTIONAL ANCHOR — agent MUST NOT edit** | Hard-denied across all permission tiers, tamper-proof by a self-referential deny i How it starts
The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Purpose
Domain-agnostic continual learning base agent. The system forms hypotheses, tracks their outcomes, builds memory of what worked and what failed, and self-evolves its reasoning capabilities over time. It serves as a reusable foundation for any domain where an autonomous agent needs to learn, reflect, and improve through experience.
Architecture
This is a Claude-native data repository — no traditional source code or build tools. Configuration and state live in YAML, JSONL, and Markdown files that Claude reads, reasons over, and updates autonomously.
Framework vs State Split (4-Tier Architecture)
core/config/— Framework definitions and parameter bounds (immutable). Contains templates, thresholds, pipeline configs,initial_state:sections, and convention reference files incore/config/conventions/.core/scripts/— Framework infrastructure scripts. All JSONL stores accessed exclusively via these scripts — the LLM never reads/edits JSONL files directly.meta/— Agent-editable meta-strategies and domain-agnostic data (independent of domain data). Metacognitive self-modification layer inspired by HyperAgents. Also includes:spark-questions.jsonl,skill-quality.yaml,skill-gaps.yaml,evolution-log.jsonl,reflection-templates.yaml,strategy-archive.yaml,config-overrides.yaml,config-changes.yaml,step-attribution.yaml,meta-knowledge/.world/— Collective domain state shared across agents within a domain. Lives at an external user-supplied path (shared drive, NAS, etc.), configured inagents/<agent>/local-paths.conf. Contains the knowledge tree, aspirations, pipeline, reasoning bank, guardrails, pattern signatures, message board, file history, changelog, conventions, sources,program.md(The Program — shared purpose), etc.agents/<agent-name>/— Per-agent private state (e.g.,agents/alpha/). Contains session state, journal, experience traces,self.md(agent identity), curriculum, developmental stage, profile, infra health, and the agent's local aspiration queue. Theagents/parent is configurable viaAGENTS_PARENT_DIR(see "Agent-dir Resolution" below).
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.
- today Changed · +1 lines · +92 tokens per session 72cc377c5a6c
- 8d ago First seen · 528 lines · 11,307 tokens per session scan B b1b7a098af1a
Claude-Mind CLAUDE.md is an instructions file published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed today), licensed MIT. It adds 11,399 tokens to every session, about $0.0570 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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.