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-report/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-report)<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-meditation-report"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-report/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-report"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-report.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 | $0.07962 |
| Opus 5.5 | $0.00000 | $0.03185 |
| Sonnet 5.5 | $0.00000 | $0.01592 |
| Haiku 4.5 | $0.00000 | $0.00796 |
Grade A, and why
crux-skill-memory-meditation-report 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRUX Skill: Memory Meditation — Report Generation
Implements the mandatory paired HTML+PDF report generation contract: Comprehensiveness Level Mapping, Anti-Homogenisation Rules, Universal Contrast, light/dark mode + print TOC, Chart.js / D3 / calculator with static fallbacks, Subject-Matter Focus rule, Init-Suggestions Honour, K10b Per-Cheap-Type Rendering Contract, headless Chrome → Chromium degradation, and the Report-Skill Respawn Protocol resume-handler.
When to Use
Load this skill when:
- The
crux-cursor-meditation-guideagent runs report generation at step 12 of the depth-0 manager workflow - The
crux-cursor-meditation-guideensemble aggregator generates the ensemble-level report (step 4 of Ensemble Aggregation) - The report skill is respawned via Dim 13 of the adversarial review (Report-Skill Respawn Protocol)
Prerequisites
- Adversarial review verdict is
PASSorPASS_WITH_ADVISORIES— never run onESCALATE comprehensiveness:payload is present — abort with: "comprehensiveness:payload required; missing from spawn prompt — caller misconfigured" if missingtheming:payload is present — abort with a clear error pointing at Theme Preflight if missing- All meditation files are available in the working directory
Comprehensiveness Level Mapping (contract)
The report-generation skill reads the comprehensiveness: payload from its spawn prompt. Every subsection that cites a content minimum (charts, infographics, calculators, section depth, leaf inclusion) reads from this payload rather than hard-coding fixed numerals.
comprehensiveness: payload fields consumed by report generation:
| # | Dimension (comprehensiveness.minima.*) |
compact |
default |
detailed |
exhaustive |
|---|---|---|---|---|---|
| 1 | minima.charts.count |
4 | 5 | 7 | 10 |
| 2 | minima.charts.types_required |
Any 4 distinct from Chart.js + D3 mix | ≥5 distinct, ≥1 D3-advanced (sunburst, sankey, force-directed, parallel-coordinates, choropleth) | ≥7 distinct, ≥2 D3-advanced, ≥1 per facet-kind: comparison, trend, distribution | ≥10 distinct, ≥3 D3-advanced, ≥1 per facet-kind: comparison, trend, distribution, composition, network/relationship, geo (when topic supports geo) |
| 3 | minima.infographics.count |
3 | 4 | 6 | 8 |
| 4 | minima.infographics.types_required |
Any 3 distinct from the existing menu | ≥4 distinct, ≥1 hierarchy, ≥1 process/flow | ≥6 distinct, ≥1 hierarchy, ≥1 process/flow, ≥1 comparison (matrix/quadrant) | ≥8 distinct, ≥1 each of: hierarchy, process/flow, comparison, taxonomy, timeline, persona |
| 5 | minima.calculators.count |
1 | 1 | 2 | 3 |
| 6 | minima.calculators.scenarios_per |
3 | 4 | 5 | 5 |
| 7 | depth3_leaf_inclusion |
summary |
summary |
verbatim_quotes |
verbatim_quotes |
| 8 | per_branch_section_depth |
consolidation_only |
branch_summary |
per_leaf_detail |
per_leaf_detail |
| 9 | citation_density |
Research=mandatory; Quick=warn_only |
Research=mandatory; Quick=warn_only |
Research=mandatory; Quick=warn_only |
Research=per_finding_table; Quick=warn_only with per-finding-table column (placeholder text for missing citations) |
| 10 | peer_review_surfacing |
consolidation_only |
consolidation_only |
named_section |
per_branch_dedicated |
| 11 | section_length_budget_tokens |
{ hero: 800, per_facet: 2500, citations: 1000 } |
{ hero: 1200, per_facet: 4000, citations: 1500 } |
{ hero: 1800, per_facet: 6500, citations: 2000 } |
{ hero: 2400, per_facet: 9500, citations: 2500 } |
| 12 | ensemble_cross_model_depth |
per_facet_cards |
per_facet_cards |
per_leaf_attribution |
per_leaf_attribution |
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 2ea7554978d0
- 2mo ago First seen · 366 lines · 0 tokens per session scan A 7e46a8d960cc
crux-skill-memory-meditation-report 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 7,962 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-report compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crux-skill-memory-meditation-reportzotoio/CRUX-Compress | Skill | 8 | 14d ago | MIT | A | 0 | Cursor |
| oma-pdffirst-fluke/oh-my-agent | Skill | 1.4k | yesterday | MIT | A | 33 | Claude Code |
| slidesfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 83 | Claude Code |
| pkf-writingPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 78 | Claude Code, Codex |
| liteparsePrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 173 | Claude Code, Codex |
| ingestPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 132 | Claude Code, Codex |
| publishingdanjdewhurst/story-skills | Skill | 392 | 2d ago | MIT | A | 204 | Claude Code |