agentmods.dev

corpus AGENTS.md

Repository instructions for coding agents working on the Corpus project, which stores knowledge in an Obsidian vault. They explain the project layout, file rules, and where the vault is located.

In plain words
What is it for?
Use them when changing Corpus code, agents, commands, or scaffolding, especially when working with the separate vault and its raw, wiki, and output folders.
Why use it?
They give different coding tools the same rules, reducing accidental edits to user content or the wrong repository.

Instructions file for CodexOpenCode

1 4mo ago A scan 901 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/agents-md
Clone the repo
git clone --depth 1 https://github.com/evb87-tech/corpus

Made for: Codex, OpenCode.

Per session 901 This file is loaded in full into every session.
When invoked 901 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 $0.00901 $0.00901
Opus 5 $0.00451 $0.00451
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured yesterday against content hash 32e94ffba421, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

corpus AGENTS.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 yesterday.

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.

AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Agent-agnostic instructions. For Claude-specific guidance, see CLAUDE.md. The rules below are equivalent — only the loading convention differs (this file is read by Codex, Gemini CLI, Aider, OpenCode, etc.).

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, notes, syntheses)
└── .obsidian/      Obsidian config

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

  1. Never modify $CORPUS_VAULT/raw/. The owner curates what enters.
  2. Only agents write to $CORPUS_VAULT/wiki/. The owner does not hand-edit.
  3. output/ never feeds back into wiki/.
  4. Wiki content is in French; sources may be EN or FR (translate at ingestion). Structural keywords (frontmatter fields, filenames, fixed H2 names) stay in English.
  5. One entity, one page in wiki/. Update; do not duplicate.
  6. Cite every claim back to a file in raw/.
  7. Surface contradictions; never harmonize silently.
  8. Never invent a source. Never complete with training-data knowledge unless the owner explicitly asks.
  9. Never produce type: synthesis as a wiki page. Synthesis goes to output/ only.
  10. Never assume the vault path. Resolve via $CORPUS_VAULT. Refuse to operate if unset.

Repo layout — monorepo of two plugins

  • corpus-core/ — the engine plugin (rules, agents, commands, plugin manifest)
  • corpus-pm/ — first use-case pack, depends on corpus-core
  • .claude-plugin/marketplace.json publishes both
  • Repo-wide docs at docs/, CLAUDE.md, AGENTS.md, CONTRIBUTING.md

Read the full file on GitHub · 62 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. yesterday First seen · 62 lines · 901 tokens per session scan A 32e94ffba421

Subscribe to this mod's changes

corpus AGENTS.md is an instructions file published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 901 tokens to every session, about $0.0045 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.

Data and AILLMPlanningclaude-codeclaude-code-marketplaceclaude-code-pluginknowledge-managementobsidian
Related

Other instructions, from other repositories

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

claude-obsidian copilot-instructions.md

Copilot instructions for AgriciDaniel/claude-obsidian: Read AGENTS.md before proposing changes. The repository is an Agent Skills package, Claude Code adapter, standard-library Python core, and deterministic vault template—not the default live user vault.

AgriciDaniel/claude-obsidian · 186 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

llm-brain CLAUDE.md

Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.

kimsanguine/llm-brain · 3,289 tokens

superbrain CLAUDE.md

Instructions for m3talux/superbrain, covering superbrain — repository rules, non-negotiables, public-facing content, versioning and workflow.

m3talux/superbrain · 566 tokens

pulse CLAUDE.md

Instructions for muhammademanaftab/pulse, covering pulse: claude context, what this is, architecture (convex-backed; not a claude code plugin), status and hard security rules (the repo is public-bound).

muhammademanaftab/pulse · 1,059 tokens