agentmods.dev

dharma-okf: Instructions file for Claude Code

CLAUDE.md

dharma-okf CLAUDE.md is an instructions file for Claude Code from dharma-okf-foundation/dharma-okf. It costs 1,981 tokens per session, scanned A, original, Apache-2.0.

A set of repository instructions for Dharma-OKF, a collection of documents following the Open Knowledge Format, a structured way to publish reusable knowledge. It explains the project's differences from the upstream specification and rules for writing concept documents.

In plain words
What is it for?
Use it when creating or editing Dharma-OKF concept and reference documents, checking metadata, or following the repository's document format.
Why use it?
It prevents agents from following misleading upstream documentation or recording human verification that automated tools are not allowed to claim.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is dharma-okf-foundation/dharma-okf's own configuration. It tells Claude Code how to work on dharma-okf itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dharma-okf configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - ../concepts/karma.md.

not rated 2repo changed 2d ago A scan 1,981 tokens original Apache-2.0
View source ↗ dharma-okf-foundation/dharma-okf cloud.google.com
Reuse

Borrowing it

Nothing to install: this file belongs to dharma-okf-foundation/dharma-okf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dharma-okf-foundation/dharma-okf/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dharma-okf-foundation/dharma-okf

Made for: Claude Code.

Wrote 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.

agentmods badge for dharma-okf CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dharma-okf-foundation/dharma-okf/claude-md/github.svg)](https://agentmods.dev/instructions/dharma-okf-foundation/dharma-okf/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dharma-okf-foundation/dharma-okf/claude-md"><img src="https://agentmods.dev/badge/instructions/dharma-okf-foundation/dharma-okf/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.

agentmods 80×15 button for dharma-okf CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dharma-okf-foundation/dharma-okf/claude-md"><img src="https://agentmods.dev/badge/instructions/dharma-okf-foundation/dharma-okf/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,981 This file is loaded in full into every session.
When invoked 1,981 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01981 $0.01981
Opus 5 $0.00991 $0.00991
Sonnet 5 $0.00396 $0.00396
Haiku 4.5 $0.00198 $0.00198

Measured 2d ago against content hash b33f0a16b2a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dharma-okf 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 · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dharma-okf — agent working rules

This repository publishes Dharma-OKF, a profile of the Open Knowledge Format. Read PROFILE.md before changing anything; it is normative and this file is its operational summary. Where the two disagree, PROFILE.md wins and this file is the bug.

Base spec: OKF v0.2 at GoogleCloudPlatform/open-knowledge-format@ad30107. Profile: dharma-okf/1.0. Corpus: 442 concept documents in 13 bundles — 310 type: Concept, 132 type: Reference.

The one thing to understand first

On OKF v0.2, the specification and the reference implementation disagree. Reading SPEC.md alone will lead you to author bundles that upstream's own tooling silently mishandles. Every rule below marked ⚠️ exists because of a specific divergence that was verified by reading upstream source, not upstream prose. Do not "correct" them back toward the spec text.

Never

These are refusals. If a task appears to require one, stop and ask.

  1. Never write verified:. It records a human review event by a tradition-bearer. Automated tooling writes generated: and nothing else. Stamping verified: during a mechanical edit asserts that a person checked a document no person checked — it converts the corpus's central trust claim into noise. (PROFILE.md §3.3)
  2. Never flatten not: to a list of strings. The term / why / instead triple is the payload, not decoration. why is the argument; instead is what a consuming agent actually executes as a prompt or filter constraint. A bare ["Fate", "Destiny"] is the abandoned v0.1 shape and destroys the field's function across 310 files. (§2.1)
  3. Never delete ## Citations body sections or their links when adding sources: frontmatter. Body links are the only source of graph edges — related: frontmatter is not traversed by link-graph consumers. Removing them silently deletes the bundle's relationship graph. Frontmatter sources is added alongside, never migrated from. (§2.5, §3.1)
  4. Never claim another producer's identity in generated.by. reference_agent/... is Google's. Use your own namespace: claude-opus-5/<version>, gemini-spark/<version>. (§2.3, base §7)
  5. Never change a document's type: value. It is Concept or Reference. Both are load-bearing: Reference is colour-matched by upstream's viewer, and the split is what makes not:-applicability checkable. (§1)
  6. Never edit files under a release tag's assumptions. main is the living vocabulary; tags are immutable snapshots. Content revisions patch-bump bundle_version and append to CHANGELOG.md. See VERSIONING.md.

Read the full file on GitHub · 135 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 Changed · +6 tokens per session b33f0a16b2a8
  2. 3d ago Changed · +41 tokens per session 6931af8f1056
  3. 9d ago First seen · 135 lines · 1,934 tokens per session scan A 5e81d30ecc6c

Subscribe to this mod's changes

dharma-okf CLAUDE.md is an instructions file published in the GitHub repository dharma-okf-foundation/dharma-okf (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,981 tokens to every session, about $0.0099 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.

ai-agentsdharmahinduismknowledge-graphopen-knowledge-formatsanatana
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 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 · 5,153 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

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

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 · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens