dogent: Instructions file for Claude Code

CLAUDE.md

dogent CLAUDE.md is an instructions file for Claude Code from yegor256/dogent. It costs 306 tokens per session, scanned A, original, MIT.

Repository instructions for dogent, a tool that checks agent instruction files such as SKILL.md and CLAUDE.md. It parses each file into typed sections, applies rules, and reports violations in a SARIF-like format.

In plain words
What is it for?
Use them when implementing or extending dogent's parser, document model, validation rules, violation reporting, and tests.
Why use it?
They make instruction-file checks consistent and ensure invalid files cause a non-zero exit status.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is yegor256/dogent's own configuration. It tells Claude Code how to work on dogent 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 dogent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yegor256/dogent. 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/yegor256/dogent/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yegor256/dogent

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 dogent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yegor256/dogent/claude-md/github.svg)](https://agentmods.dev/instructions/yegor256/dogent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yegor256/dogent/claude-md"><img src="https://agentmods.dev/badge/instructions/yegor256/dogent/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 dogent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yegor256/dogent/claude-md"><img src="https://agentmods.dev/badge/instructions/yegor256/dogent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 306 This file is loaded in full into every session.
When invoked 306 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 $0.00306 $0.00306
Opus 5.5 $0.00122 $0.00122
Sonnet 5.5 $0.00061 $0.00061
Haiku 4.5 $0.00031 $0.00031

Measured 2mo ago against content hash fe2bdec5abe3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dogent 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 2mo 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 · 59 lines

What it actually says

Dogent

Lint agentic manifesto files like SKILL.md and CLAUDE.md.

Mission

Demand extreme quality, reject every compromise. Treat each line as one instruction, nothing else. Run standalone by default, call AI only when token exists.

Pipeline

Parse one manifesto into fragments. Wrap fragments into one Document. Apply every rule to that Document. Gather violations, render SARIF-like output. Exit non-zero once any violation appears.

Parsing

Read manifesto line by line, never through grammar. Track context: inside fence, inside bullet list. Classify each line from current context. Emit fragments in original order.

Fragments

Model each piece as one immutable fragment. Use Header for section heading lines. Use Prose for single instruction lines. Use Bullets for grouped bullet items. Use Snippet for fenced code blocks. Dispatch through accept, expose nothing else. Forbid type checks, casting, reflection.

Rules

Take whole Document, return violations. Walk fragments through double dispatch. Keep every rule final and immutable. Add fresh rules without touching old rules.

Checks

Demand every line carry one instruction. Group instructions under short sections. Limit section names to three words. Cap every line at eighty symbols. Phrase every line as one command. Strip articles, noise, bloated wording. Favor simple grammar over ambiguity.

Quality

Write tests before changing behavior. Hold one assertion per test. Map test files one to one with features. Run dogent against itself inside CI.

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. 2mo ago First seen · 59 lines · 306 tokens per session scan A fe2bdec5abe3

Subscribe to this mod's changes

dogent CLAUDE.md is an instructions file published in the GitHub repository yegor256/dogent (8 stars, last pushed today), licensed MIT. It adds 306 tokens to every session, about $0.0012 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 2026-08-31.

Related

dogent CLAUDE.md compared with instructions from other repositories

dogent CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dogent CLAUDE.mdyegor256/dogentInstructions file8todayMITA306Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file279ktodayMITA4,325Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot