claude-plugins CLAUDE.md

claude-plugins CLAUDE.md is an instructions file for coding agents from xentivo/claude-plugins. It costs 1,011 tokens per session, scanned A, original, MIT.

A set of repository instructions for Claude Code, including rules for persistent session memory and distributing three related plugins from a marketplace.

In plain words
What is it for?
Use it to restore or save Claude Code session context, generate a repository map, and manage the marketplace containing the memory, human-writing, and related plugins.
Why use it?
It records where lasting decisions and session notes belong, helping work continue consistently between sessions.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/xentivo/claude-plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/xentivo/claude-plugins

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 claude-plugins CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xentivo/claude-plugins/claude-md.svg)](https://agentmods.dev/instructions/xentivo/claude-plugins/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xentivo/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/xentivo/claude-plugins/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,011 This file is loaded in full into every session.
When invoked 1,011 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 5.1 $0.01011 $0.01011
Opus 5 $0.00505 $0.00505
Sonnet 5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 5d ago against content hash 5f7361c73ac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-plugins 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 5d 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reguły dla Claude Code

Pamięć Claude

Trwała pamięć między sesjami żyje w docs/claude-memory/ (README.md — zasady, decisions.md — dziennik decyzji, sessions/ — logi sesji).

  • Na początku sesji uruchom Skill resume (/claude-memory:resume), by odtworzyć kontekst, zanim zaczniesz pracę.
  • Na końcu sesji uruchom Skill save (/claude-memory:save), by zapisać log sesji i ew. nową decyzję.
  • Strukturalną mapę repo trzyma graph.json (korzeń) generowany lokalnie przez generator wbudowany w Skill graph (generate_graph.py w folderze skilla). Przed czytaniem wielu plików uruchom Skill graph (/claude-memory:graph) i odpytaj mapę zamiast skanować repo. Zero zewnętrznych zależności.
  • Trwałe ustalenia traktuj jak źródło prawdy „dlaczego tak”; nie duplikuj tu treści — w razie sprzeczności pierwszeństwo ma CLAUDE.md.

Dystrybucja: marketplace xvo-plugins

To repo jest marketplace xvo-plugins (.claude-plugin/marketplace.json w korzeniu) i źródłem trzech pluginów:

  • plugins/claude-memory/ — skille resume, save, graph; generator graph.json i szablony pamięci wbudowane obok SKILL.md.
  • plugins/czlowiek/ — skill czlowiek (redakcja polskich tekstów) plus cienka komenda commands/humanizuj.md, która ten skill woła. Autorka: Izabella Pyrkosz, własny LICENSE przy pluginie.
  • plugins/pipeline/ - skille bramka-pr, deploy, sekrety plus komenda commands/xvo-zbuduj-pipeline.md. Procedura, nie treść normatywna: reguły żyją w content/ci-pipeline.md w xentivo/mcp-org-rules i idą przez MCP, a skille dociągają je przez get_rule. Kopiowanie reguł do SKILL.md dałoby drugą wersję prawdy, która rozjedzie się przy pierwszej poprawce zasady.

Konwencja: każdy plugin ma własny katalog w plugins/<nazwa>/ z manifestem .claude-plugin/plugin.json i wpis w marketplace.json. Komponenty są autowykrywane z skills/, commands/, agents/, hooks/hooks.json. Katalog .claude-plugin/ w korzeniu repo jest zarezerwowany — czytany jest z niego wyłącznie marketplace.json, więc nie wrzucaj tam pluginu (zdarzyło się dwa razy przy „Add files via upload" w GitHub UI; plugin był wtedy niewidoczny, raz zgubił się plugin.json).

Read the full file on GitHub · 61 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. 5d ago First seen · 61 lines · 1,011 tokens per session scan A 5f7361c73ac6

Subscribe to this mod's changes

claude-plugins CLAUDE.md is an instructions file published in the GitHub repository xentivo/claude-plugins (3 stars, last pushed 10d ago), licensed MIT. It adds 1,011 tokens to every session, about $0.0051 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.