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/0sxd/archive-openbrain/claude-mdgit clone --depth 1 https://github.com/0SxD/archive-openbrainWrote 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/0sxd/archive-openbrain/claude-md)<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>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 | $0.00834 | $0.00834 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00083 | $0.00083 |
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.
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 ledgermemory/long_term.md— verified findings (consolidated from short_term)memory/todos.md— persistent task listmemory/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
- No public actions without explicit approval. (rule 00)
- Trinity is a DIALECTIC, not a pipeline. Logos and Pathos fight. Ethos provides the corridors and criteria.
- Always cite. No claims without third-party sources.
- Append-only memory. Never delete from long-term. Overflow to archival.
- 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 |
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 · 84 lines · 834 tokens per session scan A 8c8e3597df91
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.
Other instructions, from other repositories
MemOS CLAUDE.md
Claude Code instructions for MemTensor/MemOS, covering claude.md, claude code entry, sub-agents and project knowledge.
MemOS AGENTS.md
AGENTS.md instructions for MemTensor/MemOS, covering agents.md, project overview, repository layout, command cheatsheet and core api.
avoid-ai-writing CLAUDE.md
Instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.