agentmods.dev

dotclaude: Instructions file for Claude Code

CLAUDE.md

dotclaude CLAUDE.md is an instructions file for Claude Code from poshan0126/dotclaude. It costs 449 tokens per session, scanned A, original, MIT.

Project guidance for maintaining a Claude Code plugin marketplace, written in Markdown, JSON, and shell scripts.

In plain words
What is it for?
Use it when changing plugins, agents, skills, rules, hooks, manifests, or marketplace validation in the dotclaude repository.
Why use it?
It records the repository’s structure, commands, design decisions, and safety rules so coding agents do not place files in the wrong locations or confuse templates with source files.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is poshan0126/dotclaude's own configuration. It tells Claude Code how to work on dotclaude 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 dotclaude configures →

not rated 871repo +2 2mo ago A scan 449 tokens original MIT
View source ↗ poshan0126/dotclaude
Reuse

Borrowing it

Nothing to install: this file belongs to poshan0126/dotclaude. 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/poshan0126/dotclaude/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/poshan0126/dotclaude

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 dotclaude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/poshan0126/dotclaude/claude-md/github.svg)](https://agentmods.dev/instructions/poshan0126/dotclaude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/poshan0126/dotclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/poshan0126/dotclaude/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 dotclaude CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/poshan0126/dotclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/poshan0126/dotclaude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 449 This file is loaded in full into every session.
When invoked 449 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 $0.00449 $0.00449
Opus 5.5 $0.00180 $0.00180
Sonnet 5.5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 2mo ago against content hash 931ff4b24bb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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 · 29 lines

What it actually says

dotclaude (this repo)

A Claude Code plugin marketplace: agents, skills, rules, and safety hooks, published from the top-level directories. There is no application code, build, or package manager here — everything is bash + markdown + JSON.

Commands

bash hooks/tests/run-all.sh          # run all hook fixture tests (requires jq)
claude plugin validate . --strict    # validate marketplace + plugin manifests

Architecture

  • Top-level agents/, skills/, rules/, hooks/ are the single source of truth. plugins/<name>/ dirs contain only a plugin.json plus relative symlinks into the top-level dirs (Claude Code dereferences marketplace-internal symlinks at install) — never put real component copies there. Plugin sources must NOT be "./": with the repo root as plugin root, default component discovery would load every skill/agent into every plugin.
  • CLAUDE.template.md is the template shipped to user projects by /setupdotclaude. This file (CLAUDE.md) is for working on the repo itself — don't confuse the two.
  • settings.json at the repo root is the template users copy to .claude/settings.json; it wires the hooks.

Key decisions

  • Versioning: each plugins/<name>/.claude-plugin/plugin.json carries semver — bump it when that plugin's components change. Marketplace entries carry NO version (plugin.json silently wins; never set both).
  • Hooks fail open (exit 0) when jq is missing, except file-protection hooks which fail closed. Hook timeout values are in seconds.
  • Agents never set model — users choose their own.

Workflow

  • Every new or modified hook MUST ship with fixtures under hooks/tests/fixtures/<hook-name>/ (see CONTRIBUTING.md).
  • After changing any manifest, skill, or agent frontmatter, run claude plugin validate . --strict.
  • Adding/renaming a skill or agent requires: marketplace entry, plugins/<name>/ (plugin.json + symlink), and the folder README.
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 · 29 lines · 449 tokens per session scan A 931ff4b24bb9

Subscribe to this mod's changes

dotclaude CLAUDE.md is an instructions file published in the GitHub repository poshan0126/dotclaude (871 stars, last pushed 2mo ago), licensed MIT. It adds 449 tokens to every session, about $0.0018 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.

Related

dotclaude CLAUDE.md compared with instructions from other repositories

dotclaude CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dotclaude CLAUDE.mdposhan0126/dotclaudeInstructions file8712mo agoMITA449Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode