dotclaude CLAUDE.md

dotclaude CLAUDE.md is an instructions file for coding agents from JHostalek/dotclaude. It costs 155 tokens per session, scanned A, original, CC0-1.0.

User-level instructions that define strict working rules for a coding agent, including concise writing, following skills, protecting shared work, and continuing after blockers are resolved.

In plain words
What is it for?
Guiding everyday coding-agent behavior in a shared workspace, especially around workflow instructions, coordination, file safety, and task completion.
Why use it?
They make the agent's behavior predictable and reduce accidental changes to other people's work or unfinished tasks.

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/jhostalek/dotclaude/claude-md
Clone the repo
git clone --depth 1 https://github.com/JHostalek/dotclaude

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 dotclaude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jhostalek/dotclaude/claude-md.svg)](https://agentmods.dev/instructions/jhostalek/dotclaude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jhostalek/dotclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/jhostalek/dotclaude/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 This file is loaded in full into every session.
When invoked 155 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 $0.00155 $0.00155
Opus 5 $0.00077 $0.00077
Sonnet 5 $0.00031 $0.00031
Haiku 4.5 $0.00015 $0.00015

Measured 4d ago against content hash f98dad07a127, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotclaude 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 4d 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 · 7 lines

What it actually says

<operating_contract>Treat these instructions as binding user-level invariants, not suggestions or style preferences.</operating_contract>

  • Be extremely concise, plain, direct, and easy to read. Sacrifice grammar, eloquence, and thoroughness for instant comprehension.
  • Skills are the workflow. Sacrifice improvisation for the sake of their instructions.
  • Treat the workspace as shared. Never hide, discard, overwrite, or rearrange work you did not create.
  • Stop and coordinate before any operation that could affect another agent’s work or the shared environment.
  • When the user resolves a blocker, resume the unfinished task immediately. Carry it through its remaining steps without waiting for a separate request to continue; stop only when the original task is complete or a new blocker remains.
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. 4d ago First seen · 7 lines · 155 tokens per session scan A f98dad07a127

Subscribe to this mod's changes

dotclaude CLAUDE.md is an instructions file published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 155 tokens to every session, about $0.0008 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