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-meditation-quick/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-meditation-quick)<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-meditation-quick"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-quick/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-meditation-quick"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-quick.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.04508 |
| Opus 5.5 | $0.00000 | $0.01803 |
| Sonnet 5.5 | $0.00000 | $0.00902 |
| Haiku 4.5 | $0.00000 | $0.00451 |
Grade A, and why
crux-skill-memory-meditation-quick 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 2mo 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRUX Skill: Memory Meditation — Quick Protocol
Implements the full Quick-mode meditation contract: 6-step parallel fan-out, step 4b 4-mode additional_focus_areas[] reconciliation, init-suggestions-{ts}.yml write, K10c in-pass reflection (same rubric as Research — warn-only citation regime carried through), comprehensiveness honouring at Quick leaf depth, and the Quick-mode steps 9–13 (identical to Research with documented relaxations).
When to Use
Load this skill when:
- The
crux-cursor-meditation-guideagent is spawned in Quick mode (--quickflag,meditateMode: "quick") - You are executing the Quick-mode depth-0 manager workflow (steps 1–13 with Quick relaxations)
- You are executing as a Quick-mode child agent at depth 1, 2, or 3 (6-step protocol)
Never load this skill in Research mode, Ensemble Aggregation mode, or Adversarial Review function.
Prerequisites
- Verify
flags.enableMemoriesis"true"(abort if not) - Confirm
comprehensiveness:payload is present — abort with: "comprehensiveness:payload required; missing from spawn prompt — caller misconfigured" if missing - Confirm
theming:payload is present — abort with a clear error pointing at Theme Preflight if missing - Confirm
modelStrategy:payload is present — abort with: "modelStrategy:payload required; missing from spawn prompt — caller misconfigured" if missing
Input Parameters (depth-0 manager, Quick mode)
Same shape as the Research depth-0 manager parameters (see the crux-skill-memory-meditation-research skill) with meditateMode: "quick". The only parameter differences are:
- No
facet-registry.ymloperations (Quick mode skips global registry) - No
citations-index.ymlinitialization (Quick mode does not maintain this file)
Input Parameters (Quick child agent, depth 1–3)
meditateMode: "quick"
workingDir: "<path>"
branchNumber: {N}
meditateDepth: {D}
maxDepth: {D} # propagated unchanged
subfocus: "<subfocus>"
subfocusSlug: "<kebab-case slug>"
subfocusIndex: {S}
parentSubfocus: "<parent's subfocus or null at depth 1>"
siblingFacets: [ ... ]
theming: { ... } # propagated unchanged — REQUIRED
comprehensiveness: { ... } # propagated unchanged — REQUIRED; abort if missing
modelStrategy: { ... } # propagated unchanged — REQUIRED; abort if missing
confirmDeepFacets: "none" | "depth_2_only" | "all_levels"
ensembleModel: "<model-slug>" # when present, propagated unchanged; per-spawn model: carrier for this branch's subtree
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.
- 2mo ago First seen · 249 lines · 0 tokens per session scan A 8ea61df9787a
crux-skill-memory-meditation-quick is a skill published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,508 tokens. 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-meditation-quick compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crux-skill-memory-meditation-quickzotoio/CRUX-Compress | Skill | 8 | 14d ago | MIT | A | 0 | 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 |