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.
npx agentmods add instructions/qbit-glitch/ccr/agents-mdgit clone --depth 1 https://github.com/qbit-glitch/ccrWrote this? Show the measurements
A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.
[](https://agentmods.dev/instructions/qbit-glitch/ccr/agents-md)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 | $0.01660 | $0.01660 |
| Opus 5 | $0.00830 | $0.00830 |
| Sonnet 5 | $0.00332 | $0.00332 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
ccr AGENTS.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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ccr CLAUDE.md — 92% identical, 6 lines differ
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 — Codex Context Reducer
MCP server giving Codex persistent memory (GCC), self-evolving playbooks (ACE), and sandboxed REPL (RLM). No API keys needed — works with Codex Max.
How To Use CCR (MCP Tools)
Memory (GCC)
- Session start:
gcc_context(level=2)to load history - After progress:
gcc_commitwith what/why/files/next - Before compaction: Commit to preserve reasoning state
- Alternatives:
gcc_branchto isolate,gcc_mergewhen decided - Search:
gcc_context(level=5, search_term="...") - Patterns: Include
patterns_learnedin commits; query withgcc_patterns
Playbook (ACE)
- Review:
ace_get_playbookthenace_update_counters(helpful/harmful tags) - Add insights:
ace_apply_deltaADD - Maintain:
ace_find_similar+ MERGE duplicates,ace_pruneharmful - Optional
weight(0.0-1.0) for proportional credit on counters - Failure lessons: include
failure_lessondict when tagging harmful
REPL (RLM)
rlm_init→rlm_execute(search_repo, get_file) →rlm_finalize
Index
index_search(query)— keyword/semantic/hybrid searchindex_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
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.
- 2d ago First seen · 121 lines · 1,660 tokens per session scan A 1ad048a138cf
ccr AGENTS.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 1,660 tokens to every session, about $0.0083 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 2026-09-01.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.