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/skills/crux-skill-memory-extract/SKILL.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/skills/zotoio/crux-compress/crux-skill-memory-extract)<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-extract"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-extract/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/skills/zotoio/crux-compress/crux-skill-memory-extract"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 374 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00061 | $0.03926 |
| Opus 5.5 | $0.00024 | $0.01570 |
| Sonnet 5.5 | $0.00012 | $0.00785 |
| Haiku 4.5 | $0.00006 | $0.00393 |
Grade A, and why
crux-skill-memory-extract 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.
How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRUX Skill: Memory Extract
Analyses execution artifacts from a completed unit of work, compares candidates against existing memories for novelty and conflicts, and presents ranked candidate facts for the user to accept, modify, or reject.
When to Use
Use this skill when:
- A unit of work (e.g. spec) has completed execution and you want to extract memories from it
- The
/crux-dreamcommand is invoked for a specific completed work item - The
crux-memory-dreamagent orchestrates a dream workflow
Prerequisites
Before any operation:
- Read config: Load
.crux/crux-memories.json. This skill needsflags.enableMemories,cruxMemories.unitOfWork,cruxMemories.dream.*(maxCandidateFacts,maxUnrelatedChanges,stateFile,workDir),cruxMemories.storage.memoriesDir/agentMemoriesDir, andcruxMemories.typePriority. Defaults and full key descriptions live in.cursor/skills/_memory-shared.md#config-referenceand.crux/crux-memories.json(authoritative). - Guard check: If
flags.enableMemoriesis not"true", refuse all operations and inform the caller that memories are disabled.
Operations
1. Verify Execution
Confirm the unit of work completed successfully before extracting memories.
Input: Path to the work item directory (e.g. specs/20260403-crux-memories/)
Path validation — CRITICAL: The work item directory MUST be a subdirectory of the configured workDir (cruxMemories.dream.workDir, default specs). If the provided path points to a directory outside workDir, abort with an error listing the available specs from workDir. Do not search .ai-ignored/specs/, .ai-ignored/executed/, or other directories.
Steps:
- Verify the work item directory exists within the configured
workDir; if not, abort and list available specs - Look for the configured
stateFile(default_execution-state.yml) inside the work item directory - Parse the state file and check the
statusfield - If status is not
complete(or equivalent success state), report the current status and abort extraction — incomplete work items should not produce memories - If no state file exists, return a
needs_user_inputresponse asking whether to proceed anyway (the work item may have been executed outside the standard workflow) — the calling agent will ask the user and resume you with the decision - Record the execution start date from the state file for use in diff analysis
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.
- 1mo ago Changed · -64 lines 6015356791c0
- 2mo ago First seen · 381 lines · 61 tokens per session scan A 1c4b5bf187b0
crux-skill-memory-extract is a skill published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 14d ago), licensed MIT. It adds 61 tokens to every session and 3,926 once invoked, about $0.0002 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 2026-08-31.
crux-skill-memory-extract compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crux-skill-memory-extractzotoio/CRUX-Compress | Skill | 8 | 14d ago | MIT | A | 61 | Cursor |
| kiro-steering-customgotalab/cc-sdd | Skill | 3.8k | 15d ago | MIT | A | 14 | Claude Code, Codex |
| [object Object]team-reflect/reflect-open | Skill | 1.6k | yesterday | MIT | A | 51 | Claude Code, Codex |
| identity-snapshotdavekilleen/Dex | Skill | 512 | 8d ago | MIT | A | 74 | Claude Code, Codex |
| daily-journalhuytieu/COG-second-brain | Skill | 1.3k | 14d ago | MIT | A | 107 | Claude Code |
| simplemem-skillaiming-lab/SimpleMem | Skill | 3.9k | 3mo ago | MIT | A | 58 | Claude Code, Codex |
| alive:session-historyalivecontext/alive | Skill | 132 | 1mo ago | MIT | A | 76 | Claude Code |