What is ccr CLAUDE.md?

Project instructions for ccr, a Claude Code context reducer that provides persistent memory, reusable playbooks, a sandboxed read-evaluate-print loop, code search, and session logging through MCP. Claude Code is an AI coding tool, and MCP lets it call external tools.

They are for using ccr's memory, playbook, repository-index, sandboxed REPL, and session-logging tools during development.

They give Claude Code a documented routine for preserving work between sessions, recording decisions, reusing successful patterns, and searching the project without loading every file at once.

ccr CLAUDE.md — Instructions file for coding agents by qbit-glitch: Project instructions for ccr, a Claude Code context reducer…

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/qbit-glitch/ccr/claude-md

Clone the repo

git clone --depth 1 https://github.com/qbit-glitch/ccr

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/qbit-glitch/ccr/claude-md.svg)](https://agentmods.dev/instructions/qbit-glitch/ccr/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/qbit-glitch/ccr/claude-md"><img src="https://agentmods.dev/badge/instructions/qbit-glitch/ccr/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,658 This file is loaded in full into every session.

When invoked 1,658 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 92% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.01658	$0.01658
Opus 5	$0.00829	$0.00829
Sonnet 5	$0.00332	$0.00332
Haiku 4.5	$0.00166	$0.00166

Measured 4d ago against content hash 0550d1ba9d33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccr 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.

Origin

This is a copy

92% identical to ccr AGENTS.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCR — Claude Context Reducer

MCP server giving Claude Code persistent memory (GCC), self-evolving playbooks (ACE), and sandboxed REPL (RLM). No API keys needed — works with Claude Max.

How To Use CCR (MCP Tools)

Memory (GCC)

Session start: gcc_context(level=2) to load history
After progress: gcc_commit with what/why/files/next
Before compaction: Commit to preserve reasoning state
Alternatives: gcc_branch to isolate, gcc_merge when decided
Search: gcc_context(level=5, search_term="...")
Patterns: Include patterns_learned in commits; query with gcc_patterns

Playbook (ACE)

Review: ace_get_playbook then ace_update_counters (helpful/harmful tags)
Add insights: ace_apply_delta ADD
Maintain: ace_find_similar + MERGE duplicates, ace_prune harmful
Optional weight (0.0-1.0) for proportional credit on counters
Failure lessons: include failure_lesson dict when tagging harmful

REPL (RLM)

rlm_init → rlm_execute (search_repo, get_file) → rlm_finalize

Index

index_search(query) — keyword/semantic/hybrid search
index_build — rebuild after code changes

Session Logger (SL)

After each response: session_log_turn(assistant_message="<your full response>") — logs this Q&A turn to .ccr/sessions.db
Review session: session_get_history() — last 20 turns of current session
Search past sessions: session_search(query="...") — full-text search all Q&A logs
Export for training: session_export(format="jsonl") — OpenAI fine-tuning format

Research & Experiment Tools (v6)

Log experiment: gcc_experiments(experiment_id=..., hypothesis_contains=..., metric_filter={...}) — query/filter experiment records stored in commits
Log decision: gcc_discuss(topic=..., hypothesis=..., decision=..., rationale=...) — persist reasoning behind design choices across sessions
List discussions: gcc_discussions(limit=20) — retrieve stored decision log
Semantic search: gcc_search(query=..., mode="hybrid") — keyword/semantic/hybrid search across all memory

Read the full file on GitHub · 121 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.

4d ago First seen · 121 lines · 1,658 tokens per session scan A 0550d1ba9d33

Subscribe to this mod's changes

ccr CLAUDE.md is an instructions file published in the GitHub repository qbit-glitch/ccr (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,658 tokens to every session, about $0.0083 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to ccr AGENTS.md, differing in 6 lines, and is treated as a copy.

Building agents Memory and context

cognirepo CLAUDE.md

Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).

ashlesh-t/cognirepo · 2,241 tokens

aeon CLAUDE.md

Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).

aeonfun/aeon · 3,720 tokens

wayland-core copilot-instructions.md

Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.

FerroxLabs/wayland-core · 823 tokens

mcp-structured-memory CLAUDE.md

Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.

nmeierpolys/mcp-structured-memory · 160 tokens

inkwell-memory CLAUDE.md

Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.

veronchenko/inkwell-memory · 2,378 tokens

memory-mcp-1file AGENTS.md

Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).

pomazanbohdan/memory-mcp-1file · 7,991 tokens