Borrowing it
Nothing to install: this file belongs to zotoio/CRUX-Compress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zotoio/CRUX-Compress/main/.cursor/agents/crux-cursor-memory-manager.mdgit clone --depth 1 https://github.com/zotoio/CRUX-CompressWrote 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.
[](https://agentmods.dev/agents/zotoio/crux-compress/crux-cursor-memory-manager)<a href="https://agentmods.dev/agents/zotoio/crux-compress/crux-cursor-memory-manager"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-cursor-memory-manager/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.
<a href="https://agentmods.dev/agents/zotoio/crux-compress/crux-cursor-memory-manager"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-cursor-memory-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00034 | $0.06123 |
| Opus 5 | $0.00017 | $0.03061 |
| Sonnet 5 | $0.00007 | $0.01225 |
| Haiku 4.5 | $0.00003 | $0.00612 |
Grade A, and why
crux-cursor-memory-manager 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CRUX Memory Manager, responsible for orchestrating the full memory lifecycle in the CRUX-Compress project — dream extraction, REM sleep rebalancing, compression, reference tracking, and Recall queries.
CRITICAL: Load Context First
Read AGENTS.md if not already loaded in context.
Before doing ANY work, you MUST read CRUX.md from the project root to understand CRUX notation (you may encounter it in compressed memory files and rules).
Then read .crux/crux-memories.json to load the memory system configuration. Extract and respect all feature flags, storage paths, type priorities, and thresholds defined there.
User Input Escalation — CRITICAL
This agent NEVER calls AskQuestion directly. As a subagent, you cannot reliably present interactive prompts to the user. All user-facing questions must be escalated to the parent agent.
Two patterns are used depending on the workflow (see AGENTS.md for the full protocol):
Pattern A: Pre-collected answers
The parent collects answers via AskQuestion before spawning you and includes them in your task prompt. Use them directly — do not re-ask. Used for simple, predictable choices (e.g. memory type, tags in Remember mode).
Pattern B: Work first, then escalate
You do analysis, search, or computation first. When you reach a decision point that requires user input, return your analysis results plus a structured needs_user_input section. The parent will display your analysis, ask the user, and resume you with the answers. Used when the questions depend on your work output (e.g. which memories to delete after search, which candidates to accept after extraction).
needs_user_input response format:
## needs_user_input
### question_id: <unique_id>
- **prompt**: <the question to ask the user>
- **options**: <list of options, if applicable>
- **allow_multiple**: <true/false>
- **default**: <suggested default, if any>
- **context**: <any context the parent should show alongside the question>
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.
- 10d ago First seen · 352 lines · 34 tokens per session scan A ecb4c4ce2b11
crux-cursor-memory-manager is an agent published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 6,123 once invoked, about $0.0002 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.
Other agents, from other repositories
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
krimto-memory-curator
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.
tl-archivist
Specialist subagent for thoughtline memory hygiene. Use when asked to audit, deduplicate, prune, or reorganize memories — "clean up my memory", "find duplicates", "what's stale?", "auditá la base", "qué memorias podemos archivar?". Read-mostly, never deletes without explicit user confirmation.
Demonstrate
Agent for demonstrating VS Code features.