agentmods.dev

ccx-context-system CLAUDE.md

ccx-context-system CLAUDE.md is an instructions file for coding agents from shck-dev/ccx-context-system. It costs 1,059 tokens per session, scanned A, original, MIT.

A guide for the ccx Claude Code plugin, which keeps per-thread project notes in STATE.md files and builds an INDEX.md dashboard from them. It also documents the plugin's commands, architecture, tests, and installation workflow.

In plain words
What is it for?
Use it when developing, testing, validating, or updating the ccx context-management plugin and its scratch notes.
Why use it?
It explains how the plugin preserves useful context between coding sessions and how to validate or refresh it. That reduces the need to reconstruct project history from memory.

Instructions file

not rated 1 1mo ago A scan 1,059 tokens original MIT
View the source file shck-dev/ccx-context-system
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/shck-dev/ccx-context-system/claude-md
Clone the repo
git clone --depth 1 https://github.com/shck-dev/ccx-context-system

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 ccx-context-system CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shck-dev/ccx-context-system/claude-md.svg)](https://agentmods.dev/instructions/shck-dev/ccx-context-system/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shck-dev/ccx-context-system/claude-md"><img src="https://agentmods.dev/badge/instructions/shck-dev/ccx-context-system/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,059 This file is loaded in full into every session.
When invoked 1,059 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 $0.01059 $0.01059
Opus 5 $0.00530 $0.00530
Sonnet 5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured 3d ago against content hash d837b68e1eef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccx-context-system 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 3d 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 · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A Claude Code plugin marketplace repo whose single plugin, ccx (plugins/ccx/), provides scratch-notebook context management for any project: per-thread STATE.md handoff docs under .scratch/<thread>/, plus a compiled INDEX.md dashboard. Everything (scripts, hooks, tests) runs under bun, regardless of the host project's language.

Commands

  • Tests: bun tests/run-tests.ts — single-file scenario harness (no test framework; ok() assertions, exits non-zero on failure). It builds fresh fixture projects in a tmpdir each run (a fake Go project on stock config + a custom-config project) and exercises every script and the backlink hook. There is no per-test runner; run the whole file.
  • Validate plugin structure: claude plugin validate ./plugins/ccx (and claude plugin validate . for the marketplace).
  • Try changes live in one session: claude --plugin-dir ./plugins/ccx.
  • Refresh an installed copy after edits: /plugin marketplace update ccx-context-system (or restart the session).

Architecture

Three layers, all under plugins/ccx/:

  1. Skills (skills/*/SKILL.md) — start-thread, save-state, tidy-scratch. Markdown with frontmatter; they inject live data at load time via !`bun "${CLAUDE_PLUGIN_ROOT}/scripts/<x>.ts"` preamble commands, then instruct the model. Skills never re-implement logic that scripts own (e.g. slugging goes through slug.ts).
  2. Scripts (scripts/*.ts) — deterministic bun CLIs the skills call: where.ts (resolved context), threads.ts / orphans.ts / scan.ts (read-only scans), slug.ts, compile-index.ts (the INDEX compiler).
  3. Hooks (hooks/hooks.json → scripts) — four: backlink-scratch-notes.ts (PostToolUse on Write: prepends a [[STATE]] wikilink to new unlinked scratch notes); auto-compile-index.ts (PostToolUse on Write|Edit: a STATE-doc write kicks a detached, .pending-debounced INDEX recompile — the INDEX saves itself); record-session-thread.ts (UserPromptExpansion on start-thread: records {display, slug, source, ts} to <scratch_root>/.sessions/<session_id>.json); state-freshness-guard.ts (Stop: work newer than the associated thread's STATE → block the stop once with "persist Status/summary first"; GRACE 10 min · THROTTLE 30 min · stop_hook_active-safe · SKIP_STATE_GUARD=1 escape). Hooks read the tool-call JSON from stdin and fail open — any parse error or unexpected input → exit 0; a hook must never crash the session — and stay silent on the pass path.

Read the full file on GitHub · 39 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. 3d ago First seen · 39 lines · 1,059 tokens per session scan A d837b68e1eef

Subscribe to this mod's changes

ccx-context-system CLAUDE.md is an instructions file published in the GitHub repository shck-dev/ccx-context-system (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,059 tokens to every session, about $0.0053 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.

Memory and contextanthropicclaude-codeclaude-code-hooksclaude-code-marketplaceclaude-code-pluginclaude-code-plugins
Related

Other instructions, from other repositories

dot-claude-plugins CLAUDE.md

Instructions for and3r817/dot-claude-plugins, covering claude.md, repository overview, core architecture principles, testing commands and run all test suites (master runner).

and3r817/dot-claude-plugins · 1,578 tokens

axiom AGENTS.md

Instructions for netopsengineer/axiom, covering agent instructions, scope, repository map, canonical sources and ownership matrix.

netopsengineer/axiom · 2,756 tokens

claude-plugins AGENTS.md

Instructions for jontsai/claude-plugins, covering agent guidelines, project overview, key constraints, plugin structure and validation.

jontsai/claude-plugins · 539 tokens

Product-Marketing-Skills CLAUDE.md

Instructions for stefanoskarakasis/Product-Marketing-Skills, covering claude.md, versioning & releases, release procedure (manual, until ci enforcement exists) and after any repo change.

stefanoskarakasis/Product-Marketing-Skills · 413 tokens

PM-Copilot-by-Product-Faculty CLAUDE.md

Claude Code instructions for Productfculty-aipm/PM-Copilot-by-Product-Faculty, covering pm copilot — global instructions, session start protocol, memory update protocol, context loading (all pm operations) and framework defaults.

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 1,191 tokens

claude-code-plugins CLAUDE.md

Claude Code instructions for qte77/claude-code-plugins, a project described as: A Claude Code plugin marketplace providing skills, rules, and scripts extracted from a production development workflow.

qte77/claude-code-plugins · 3 tokens