Borrowing it
Nothing to install: this file belongs to jame581/LogseqBrain. 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/jame581/LogseqBrain/main/CLAUDE.mdgit clone --depth 1 https://github.com/jame581/LogseqBrainWrote 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/jame581/logseqbrain/claude-md)<a href="https://agentmods.dev/instructions/jame581/logseqbrain/claude-md"><img src="https://agentmods.dev/badge/instructions/jame581/logseqbrain/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jame581/logseqbrain/claude-md"><img src="https://agentmods.dev/badge/instructions/jame581/logseqbrain/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02667 | $0.02667 |
| Opus 5.5 | $0.01067 | $0.01067 |
| Sonnet 5.5 | $0.00533 | $0.00533 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade A, and why
LogseqBrain 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 7d 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 — 70 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.
What this repo is
A Claude Code plugin (logseq-brain) that gives Claude persistent memory via a user-owned Logseq graph. The shipped plugin is the plugin/ folder (plugin/.claude-plugin/plugin.json, plugin/skills/, a short README.md and LICENSE); everything else at the repo root (tests, evals, tools, docs, this file) is dev-only and never reaches installers. Paths below like skills/<name>/SKILL.md are relative to plugin/. The plugin is markdown skills (skills/<name>/SKILL.md), .claude-plugin/plugin.json, and, since v0.11.0, one POSIX sh + awk helper: skills/_shared/bin/brain plus skills/_shared/lib/*.awk. Claude does the judgment (what to save, the prose). The helper does every mechanical step: section measurement, the digest Map, caps, scoped search, lint, the activity line. This deliberately reverses the earlier "no runtime code" rule, within a narrow boundary: POSIX sh/awk only, no new dependencies, and the script writes exactly four kinds of line: the Map line, one activity bullet, one ## Sessions bullet, and the parenthetical of a project's pages/Index.md one-liner (docs/superpowers/specs/2026-09-11-v0.11.0-design.md; the last two since v0.12.0, docs/superpowers/specs/2026-09-25-v0.12.0-design.md D1).
Target: Logseq OG (the markdown version) only. Logseq split in 2026 — OG moved to https://github.com/logseq/og and is in maintenance mode (security and Electron upgrades, no new features), while the DB/SQLite version continues at the original repo. There is no API or CLI for file graphs (@logseq/cli serves DB graphs only), so all leverage here is file layout, property discipline, and the helper's own awk search. Do not propose DB-version features.
The plugin is distributed via the skillsmith marketplace, the Gemini extension URL, and (for Cowork) a locally-built logseq-brain.plugin zip. The .plugin archive is a build artifact — gitignored (*.plugin), not checked in. Edit files under plugin/, never inside an archive. Rebuild it from committed content after every release — git archive --format=zip -o logseq-brain.plugin HEAD:plugin — nothing else keeps it current, and a stale one silently ships old skills to Cowork.
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.
- 7d ago Changed · +1 lines · +178 tokens per session 2fc8cf2f69c7
- 1mo ago Changed 4aa9b2bb0ee6
- 1mo ago Changed · +221 tokens per session b0ecda500b88
- 1mo ago Changed · +1 lines · +87 tokens per session b2b0c76c93ff
- 1mo ago Changed · -7 lines · -233 tokens per session 91402a06d40c
- 2mo ago First seen · 75 lines · 2,414 tokens per session scan A 011b83177fa4
LogseqBrain CLAUDE.md is an instructions file published in the GitHub repository jame581/LogseqBrain (18 stars, last pushed 7d ago), licensed MIT. It adds 2,667 tokens to every session, about $0.0107 per session on Opus 5.5. 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
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.