CRUX-Compress: Agent for Claude Code

.cursor/agents/crux-memory-forget.md

crux-memory-forget is an agent for Claude Code, Cursor from zotoio/CRUX-Compress. It costs 66 tokens per session (898 once invoked), scanned A, original, MIT.

A memory-deletion agent for CRUX that finds memories from an ID, name, path, search, or full listing, then deletes confirmed matches. CRUX is a project memory system, and deletion is treated as irreversible.

In plain words
What is it for?
Use it to locate outdated or unwanted memories and remove the confirmed files and their tracking references.
Why use it?
It provides a confirmation step before removing stored project knowledge and rebuilds the memory index afterward.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions AGENTS.md.

This is zotoio/CRUX-Compress's own configuration. It tells Claude Code and Cursor how to work on CRUX-Compress itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CRUX-Compress configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/zotoio/CRUX-Compress/main/.cursor/agents/crux-memory-forget.md
Clone the repo
git clone --depth 1 https://github.com/zotoio/CRUX-Compress

Made for: Claude Code, Cursor.

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 crux-memory-forget

README.md
[![agentmods](https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-memory-forget/github.svg)](https://agentmods.dev/agents/zotoio/crux-compress/crux-memory-forget)
Your own site
<a href="https://agentmods.dev/agents/zotoio/crux-compress/crux-memory-forget"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-memory-forget/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.

agentmods 80×15 button for crux-memory-forget

Your own site · 80×15
<a href="https://agentmods.dev/agents/zotoio/crux-compress/crux-memory-forget"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-memory-forget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00066 $0.00898
Opus 5.5 $0.00026 $0.00359
Sonnet 5.5 $0.00013 $0.00180
Haiku 4.5 $0.00007 $0.00090

Measured 1mo ago against content hash 27113ba3a755, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crux-memory-forget 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 1mo 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.

.cursor/agents/crux-memory-forget.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the CRUX Forget agent — responsible for deleting memories from the corpus. This is a destructive, irreversible operation. You are spawned by the /crux-forget command; you NEVER call AskQuestion directly.

CRITICAL: Load Context First

Read AGENTS.md if not already loaded in context.

If your task prompt includes a context_manifest stanza, honour it — skip re-reads of files marked loaded. Otherwise:

  • Read CRUX.md only if you need to display compressed memory bodies during confirmation.
  • Read .crux/crux-memories.json to load configuration (feature flags, storage paths).

User-Input Escalation

This agent NEVER calls AskQuestion. All user interaction is handled by the parent (/crux-forget command).

  • Primary pattern: Pattern B (work first, then escalate) — resolve input to matching memories, then return the match list with needs_user_input for parent-driven confirmation before deletion.
  • Resume: Parent collects the confirmed deletion list and resumes this agent to apply deletions.

See .cursor/skills/_memory-shared.md#user-input-escalation for the canonical needs_user_input YAML contract.

Skills Used

Load each skill by name before invoking:

Skill Purpose
crux-skill-memory-index Load the index for resolution; rebuild after deletions
crux-skill-memory-crud Read matches for display; delete memory files and reference trackers

Workflow

Invoked as /crux-forget <id|slug|path|"query"|∅>:

First invocation (resolve matches):

  1. Guard check: enableMemories must be "true" — abort with a message if not.
  2. Parse input: Determine resolution strategy (by ID, slug, path, search query, or list-all if empty).
  3. Resolve: Find matching memory files. If no matches, return a message and stop.
  4. Return matches: For each match, return: ID, title, type, strength, source, path.
  5. Return needs_user_input: Ask parent to confirm which memories to delete.

Resumed (apply deletions):

Read the full file on GitHub · 73 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. 1mo ago First seen · 73 lines · 66 tokens per session scan A 27113ba3a755

Subscribe to this mod's changes

crux-memory-forget is an agent published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 14d ago), licensed MIT. It adds 66 tokens to every session and 898 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-26.

Related

crux-memory-forget compared with agents from other repositories

crux-memory-forget next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
crux-memory-forgetzotoio/CRUX-CompressAgent814d agoMITA66Claude Code, Cursor
agent-orchestration-context-managerwshobson/agentsAgent42kyesterdayMITA66Claude Code
00-session-bootstrapassafkip/kipi-systemAgent1312d agoMITA21Claude Code
sdd-testerchohra-med/expo_boilerplateAgent361mo agoMITA61Claude Code
tp-session-restorerDigital-Threads/token-pilotAgent517d agononeA57Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code