agentmods.dev

dory: Instructions file for Claude Code

CLAUDE.md

dory CLAUDE.md is an instructions file for Claude Code from deeflect/dory. It costs 492 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude coding agents working on the public Dory code repository. It covers how agents should operate, follow codebase rules, protect private information, and handle commits and pull requests.

In plain words
What is it for?
Following Dory’s search and session practices, checking Python changes with Ruff and pytest, and handling OpenClaw plugin updates, commits, and pull requests.
Why use it?
It gives agents consistent project-specific guidance instead of making them infer rules from scattered files. It also helps prevent private data from being copied into public project materials.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md; built for openclaw.

This is deeflect/dory's own configuration. It tells Claude Code how to work on dory 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 dory configures →

not rated 13repo 4mo ago A scan 492 tokens original MIT
View source ↗ deeflect/dory dory.deeflect.com
Reuse

Borrowing it

Nothing to install: this file belongs to deeflect/dory. 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/deeflect/dory/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/deeflect/dory

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 dory CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/deeflect/dory/claude-md"><img src="https://agentmods.dev/badge/instructions/deeflect/dory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 492 This file is loaded in full into every session.
When invoked 492 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 $0.00492 $0.00492
Opus 5.5 $0.00197 $0.00197
Sonnet 5.5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 1mo ago against content hash 92b735eb805f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dory 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 1mo 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 · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Agent Guide

Claude agents should follow AGENTS.md. This file adds Claude-specific reminders for working in the public Dory repository.

Operating Mode

  • Use Dory MCP tools directly when available. Start a new session, post-compaction continuation, or real task switch with dory_wake(profile="coding", budget_tokens=1200) for code work; do not rerun wake on every turn when the wake block is still in context.
  • Prefer dory_search followed by exact dory_get before making claims about project state, prior decisions, or current runtime assumptions.
  • Do not copy private Dory memory into repository files. Public docs, tests, evals, examples, and issue templates must use synthetic data.
  • Keep responses and patches scoped. If a change is cross-cutting, state the plan briefly and then implement.

Codebase Norms

  • Python code targets Python 3.12 and is managed with uv.
  • Run uv run ruff check <paths> for touched Python paths.
  • Run focused uv run pytest ... tests for behavior changes; use uv run pytest -q when the change has broad impact.
  • For OpenClaw plugin changes, update packages/openclaw-dory/src/index.ts, run npm install && npm run build locally or npm ci && npm run build in CI, and include the rebuilt packages/openclaw-dory/dist/index.js.
  • Do not edit generated or local runtime files unless the task explicitly asks for them.

Public-Safety Rules

  • No real tokens, API keys, bearer values, private hostnames, personal identifiers, or local absolute paths.
  • No real private memories in fixtures. Use names like Atlas, Demo User, Example Project, and placeholder domains like example.com.
  • Do not add raw session logs or private corpus material to the public tree.
  • Run uv run python scripts/release/check-public-safety.py --path <path> for changed public docs, fixtures, evals, examples, or release artifacts.

Commit And PR Rules

  • Only commit when the user asks.
  • Use Conventional Commits with a clear scope when useful, for example docs: add contribution guide or fix(search): rank canonical hits first.
  • Include verification in the final response and in PR notes.
  • Mention any skipped checks explicitly.

Read the full file on GitHub · 33 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. 1mo ago First seen · 33 lines · 492 tokens per session scan A 92b735eb805f

Subscribe to this mod's changes

dory CLAUDE.md is an instructions file published in the GitHub repository deeflect/dory (13 stars, last pushed 4mo ago), licensed MIT. It adds 492 tokens to every session, about $0.0020 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.

Claude Codeagentsai-agentscodexdockerfastapi
Related

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).

microsoft/vscode · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

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).

microsoft/vscode · 2,731 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 · 4,261 tokens