archive-openbrain CLAUDE.md

archive-openbrain CLAUDE.md is an instructions file for coding agents from 0SxD/archive-openbrain. It costs 834 tokens per session, scanned A, original, MIT.

Project governance instructions for OpenBrainLM, a harness for large language models. A harness is the surrounding rules, memory, tools, and agent workflow that guide a model's work.

In plain words
What is it for?
It is for following the project's Trinity reasoning mode, managing short- and long-term memory, using self-learning workflows, and applying its governance rules.
Why use it?
It explains how the project combines structured debate, persistent memory, research, verification, and agent coordination.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/0sxd/archive-openbrain/claude-md
Clone the repo
git clone --depth 1 https://github.com/0SxD/archive-openbrain

Wrote 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.

agentmods badge for archive-openbrain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0sxd/archive-openbrain/claude-md.svg)](https://agentmods.dev/instructions/0sxd/archive-openbrain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/0sxd/archive-openbrain/claude-md"><img src="https://agentmods.dev/badge/instructions/0sxd/archive-openbrain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 834 This file is loaded in full into every session.
When invoked 834 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00834 $0.00834
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 4d ago against content hash 8c8e3597df91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archive-openbrain 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.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenBrainLM — Subproject Governance

Auto-loaded by Claude Code when working in this directory. Parent governance: C:\apps_ai\CLAUDE.md (inherits all global rules).


What Is This

A harness for large language models. Three parts: Trinity (dialectic reasoning), Memory (persistence across sessions), Self-Learning Loop (research + verification).

The harness is MD files, rules, skills, hooks, memory, and agent dispatch. LM-agnostic — works with any backend.

Owner

See parent C:\apps_ai\CLAUDE.md for owner profile.

The Harness (What's Operational)

Trinity Mode

  • Ethos — evidence corridors + rules + evaluation criteria (set per task)
  • Pathos — the mission (Opus doing work, managing agents and memory)
  • Logos — the gates (Sonnet agent checking work against Ethos)
  • Trinity is a DIALECTIC, not a pipeline. The structured disagreement IS the reasoning.
  • Spec: memory/trinity_mode_spec.md — AUTHORITATIVE

Memory

  • memory/short_term.md — session activity ledger
  • memory/long_term.md — verified findings (consolidated from short_term)
  • memory/todos.md — persistent task list
  • memory/connections.md — what works/doesn't, cross-refs
  • Auto-consolidation at session breakpoints and end

Self-Learning Loop

  • corridor → verify → cite → save → explore/learn
  • Corridors: NotebookLM (1-2 assigned), arXiv, GitHub, Context7
  • Source hierarchy: arXiv → top-tier academics → open source GitHub
  • Loop count and depth set per task

Rules

  1. No public actions without explicit approval. (rule 00)
  2. Trinity is a DIALECTIC, not a pipeline. Logos and Pathos fight. Ethos provides the corridors and criteria.
  3. Always cite. No claims without third-party sources.
  4. Append-only memory. Never delete from long-term. Overflow to archival.
  5. ASK before expanding scope. Corridors, notebooks, research direction — ASK if not specified.

Key Files

File Purpose
OPEN_BRAIN.md Core principles (append-only)
memory/trinity_mode_spec.md Trinity Mode operational spec
memory/short_term.md Session activity
memory/long_term.md Verified findings
memory/todos.md Persistent tasks
memory/connections.md Cross-refs, what works/doesn't

Read the full file on GitHub · 84 lines

Changes

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.

  1. 4d ago First seen · 84 lines · 834 tokens per session scan A 8c8e3597df91

Subscribe to this mod's changes

archive-openbrain CLAUDE.md is an instructions file published in the GitHub repository 0SxD/archive-openbrain (2 stars, last pushed 4mo ago), licensed MIT. It adds 834 tokens to every session, about $0.0042 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.