ragmark CLAUDE.md

Repository instructions for ragmark, a local search system for Markdown notes connected by wikilinks such as [[note-name]]. They define operating rules, design boundaries, and checks for autonomous coding work.

In plain words
What is it for?
Use them when modifying ragmark to keep its search layers separate, preserve local-only query behavior, and follow its testing rules.
Why use it?
They give coding agents the project’s rules and protect important quality checks and safety requirements from being changed casually.

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/cdcoonce/ragmark/claude-md
Clone the repo
git clone --depth 1 https://github.com/cdcoonce/ragmark
Per session 1,314 This file is loaded in full into every session.
When invoked 1,314 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 $0.01314 $0.01314
Opus 5 $0.00657 $0.00657
Sonnet 5 $0.00263 $0.00263
Haiku 4.5 $0.00131 $0.00131

Measured yesterday against content hash b3f7b5cb692e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ragmark 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 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.

CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ragmark — Agent Operating Rules

ragmark is local-first retrieval over markdown / [[wikilink]] vaults — hybrid (vector + lexical) chunk search, a documented note-level similarity view, wikilink-aware context expansion, and a first-party MCP surface. Embeddings run locally (fastembed); the package makes no network egress at query time. Sibling of graphmark, which it consumes for deterministic graph reads.

This file governs autonomous (afk) work in this repo. It is the contract.

Non-negotiables

  • The quality oracle is the golden-query set, and it is executor-untouchable. The golden data file is hand-curated by the owner (it lives vault-side, never in this repo — vault note content never ships). You may run it (ragmark golden), you may never generate, edit, or "fix" golden data. It grows only by a human adding the reproducing query for a found defect. There is deliberately NO parity oracle against the predecessor (improve-during-cutover, the-vault#143) — this harness and the invariants below are the only safety mechanism.
  • Safety invariants are permanent. No silent embedding truncation (total embedded chars == total chunkable chars — the predecessor silently dropped 27.8%); every indexed note retrievable; chunk↔vector conservation; context gating never leaks. Assertions bind at rank/set level with the model pinned via the index manifest — never at vector bytes.
  • The gating suite is teeth-checked, in CI. scripts/teeth_check.py re-runs the gating-marked tests with the filter defanged and requires red. A gating test that stays green with the filter off is a build failure. Never weaken a gating test to make teeth pass.
  • Implement within the seeded interfaces. model.py, config.py, gate.py's boundary, and the module seams define the shape; the MCP face (names, args, annotations) is a decided contract (the-vault#142) pinned by tests/test_mcp_face.py. Do not redesign boundaries or rename their types. Exception: an issue that explicitly directs a seeded-surface change (a human-triaged decision, recorded in the issue) wins — follow the issue.
  • Owed-behavior xfails are conductor-owned. tests/test_contract.py marks unimplemented seams with strict xfails. When your slice implements one, the xfail XPASSes and fails the suite — the same PR must replace it with real behavior tests (pre-frozen by the conductor where the slice plan says so).
  • TDD, always. Failing test first, watch it fail, minimum to pass, refactor. Small, single-purpose PRs. Conventional commits; stage explicitly.
  • Human merge gate. Nothing merges without human review.

Read the full file on GitHub · 85 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 · 85 lines · 1,314 tokens per session scan A b3f7b5cb692e

Subscribe to this mod's changes

ragmark CLAUDE.md is an instructions file published in the GitHub repository cdcoonce/ragmark (0 stars, last pushed 23d ago), licensed MIT. It adds 1,314 tokens to every session, about $0.0066 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens