agentmods.dev

corpus CLAUDE.md

Project instructions for a code engine that maintains an LLM-curated second brain: a searchable collection of notes and summaries. It separates the public engine from a user's private Obsidian vault, a folder of linked notes.

In plain words
What is it for?
Use them when developing the corpus engine, initializing a vault, processing source notes, or writing compiled wiki pages and deliverables.
Why use it?
They protect private user content and keep the engine's files, rules, and generated pages in the correct places.

Instructions file

1 4mo ago A scan 1,081 tokens original MIT
View the source file evb87-tech/corpus
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/evb87-tech/corpus/claude-md
Clone the repo
git clone --depth 1 https://github.com/evb87-tech/corpus
Per session 1,081 This file is loaded in full into every session.
When invoked 1,081 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 $0.01081 $0.01081
Opus 5 $0.00541 $0.00541
Sonnet 5 $0.00216 $0.00216
Haiku 4.5 $0.00108 $0.00108

Measured 2d ago against content hash 7eb8395208b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

corpus 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 2d 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

corpus — engine for an LLM-curated second brain

You are the custodian of a second brain that follows the Karpathy LLM-wiki pattern, extended with the workshop's anti-lissage spec.

Two repos, one system

  • This repo (corpus) is the engine: code, agents, rules, slash commands, scaffolding. Public. No user content.
  • The vault is a separate Obsidian directory the user owns and tracks in their own (typically private) git repo. Contains raw/, wiki/, output/, .obsidian/. The engine operates on it via the CORPUS_VAULT env var.
$CORPUS_VAULT/
├── raw/            sources (read-only for agents)
├── wiki/           compiled pages (agent-only writes, French content)
├── output/         deliverables (briefs, syntheses)
└── .obsidian/      Obsidian config (vault-local)

A user runs /init-vault <path> once to scaffold a fresh vault, sets export CORPUS_VAULT=<path>, then uses the slash commands. Their vault never enters this repo.

Hard rules — never break these

  • Never write into $CORPUS_VAULT/raw/. Read-only. The owner curates what enters.
  • Only you write to $CORPUS_VAULT/wiki/. The owner does not hand-edit. If they have, ask before overwriting.
  • output/ never feeds back into wiki/. Wiki = what sources said. Output = what the owner concludes.
  • Wiki content is in French. Sources may be EN or FR; translate to FR at ingestion. Verbatim quotes stay in source language. Structural keywords (frontmatter, fixed H2 names, filenames) stay English.
  • Filenames: lowercase-kebab-case, ASCII, no accents.
  • Never invent a source. Every claim traces to a file in raw/.
  • Never harmonize contradictions silently. Surface, attribute, preserve.
  • Never produce type: synthesis as wiki. Synthesis lives in output/ only.
  • Never silently complete with training-data knowledge. If the wiki is silent, say so.
  • Never assume vault path. Always resolve via $CORPUS_VAULT. Refuse to operate if unset.

Read the full file on GitHub · 68 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. 2d ago First seen · 68 lines · 1,081 tokens per session scan A 7eb8395208b4

Subscribe to this mod's changes

corpus CLAUDE.md is an instructions file published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,081 tokens to every session, about $0.0054 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.

LLMMemory and contextclaude-codeclaude-code-marketplaceclaude-code-pluginknowledge-managementobsidian
Related

Other instructions, from other repositories

claude-obsidian GEMINI.md

Gemini CLI instructions for AgriciDaniel/claude-obsidian: Read AGENTS.md as the canonical host-neutral contract. Skills live in skills/ /SKILL.md and the portable core lives in claudeobsidian/.

AgriciDaniel/claude-obsidian · 219 tokens

obsidian-mind CLAUDE.md

Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.

breferrari/obsidian-mind · 9,405 tokens

obsidian-mind AGENTS.md

AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.

breferrari/obsidian-mind · 1,145 tokens

obsidian-llm-wiki AGENTS.md

Instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.

green-dalii/obsidian-llm-wiki · 7,700 tokens

third-brain-v7-skills CLAUDE.md

Instructions for Mark393295827/third-brain-v7-skills, covering third brain v8.1 skills — claude code, v8.1 multi-domain taxonomy specification, 20 core skills overview, 📥 knowledge pipeline and 🔄 daily loop.

Mark393295827/third-brain-v7-skills · 1,124 tokens

memex-plugin CLAUDE.md

Instructions for linxule/memex-plugin, covering memex - personal knowledge base, quick start, check vault status, search for something (rrf scoring is default) and search recent docs only (7d, 2w, 3m).

linxule/memex-plugin · 2,575 tokens