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-coordination/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-coordination)<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-meditation-coordination"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-coordination/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-coordination"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-coordination.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 | $0.05422 |
| Opus 5.5 | $0.00000 | $0.02169 |
| Sonnet 5.5 | $0.00000 | $0.01084 |
| Haiku 4.5 | $0.00000 | $0.00542 |
Grade A, and why
crux-skill-memory-meditation-coordination 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRUX Skill: Memory Meditation — Coordination
Implements all file-based coordination primitives for the meditation system: artefact filename grammar (18 rows post-richness), placeholder definitions, prefix-glob polling rule, never-hard-code report.{html,pdf} invariant, process retrospective template, Branch & Leaf Index template (single-model and ensemble variants), and the ensemble working-directory structure.
When to Use
Load this skill whenever the crux-cursor-meditation-guide agent:
- Reads, writes, or links any working-directory artefact
- Needs to poll for branch outputs or report files
- Needs to construct filenames from placeholders
- Needs to append the Branch & Leaf Index to
facets.md - Needs to write the process retrospective
This is the leaf utility skill — all five other meditation skills reference it for filename grammar and polling rules.
Artefact Filename Table (18 rows post-richness)
All artefacts in the meditation working directory follow these filename patterns:
| Artefact | Filename pattern | Notes |
|---|---|---|
| Top-level facets (initial, pre-confirmation) | facets-pending-{ts}.yml |
Deleted after the user confirms via combined Pattern-B askQuestion; schema extended to carry all 4 blocks (facets + sections + visualisations + additional_focus_areas) |
| Top-level facets (final, post-confirmation) | facets.md |
Single navigational entry point; updated post-consolidation with the Branch & Leaf Index |
| Init suggestions (confirmed payload) | init-suggestions-{ts}.yml |
Written by depth-0 manager during step 4b resume (after combined Pattern-B askQuestion resolves); schema: confirmed_sections + confirmed_visualisations + additional_focus_areas blocks; read by report-generation contract and adversarial reviewer Dim 13; linked from facets.md Branch & Leaf Index ## Top-level artifacts |
| Branch (depth 1, 2, 3) | branch-{N}-depth-{D}-sub-{S}-{slug}-{yyyymmddHHMMSS}.md |
D ∈ {1,2,3}; S = 0 at depth 1, S ∈ {1,2,3} at depth 2, S ∈ {1,...,9} at depth 3 |
| Branch (intermediate, Phase B working draft) | branch-{N}-depth-{D}-sub-{S}-{slug}-{ts}-findings.md |
Research mode only; deleted after Phase G promotion |
| Peer review (Research mode) | branch-{N}-peer-review-{branchSlug}-{ts}.md |
One per branch |
| Pending deep-facet confirmation request | pending-facets-branch-{N}-depth-{D}-sub-{S}-{ts}.yml |
Only when confirmDeepFacets ≠ none; D is the parent agent's depth |
| Confirmed deep-facet response | confirmed-facets-branch-{N}-depth-{D}-sub-{S}-{ts}.yml |
Same path-id and {ts} as the pending file |
| Adversarial review iteration | review-pre-report-{ts}-iter-{N}.md |
N ∈ {1, 2, 3}; iteration cap |
| Finalisation enhancements (single-model) | finalisation-enhancements.yml |
Written by depth-0 manager during step 8 consolidation reflection (in-pass, no extra read); top-5 ranked candidates; calling agent updates in place with accepted / treatment / decided_at_utc after Q-Finalisation-Enhancements resolves; linked from facets.md Branch & Leaf Index ## Top-level artifacts |
| Finalisation enhancements (ensemble per-tree) | {model-subdir}/finalisation-enhancements.yml |
Written by per-tree depth-0 consolidation manager before returning to ensemble aggregator; carries source_tree: + surfaced_to_root: null placeholder (aggregator fills); NO per-tree askQuestion fires |
| Follow-up artefact: additional meditation | follow-up-meditation-{ts}.yml |
Written by calling agent after Q-Finalisation-Enhancements resolves for additional_meditation items with treatment ∈ {queue, spawn_now}; {ts} is the calling-agent write timestamp |
| Follow-up artefact: extracted spec | follow-up-spec-{ts}.yml |
Written by calling agent for extracted_spec items with treatment ∈ {queue, spawn_now} |
| Follow-up artefact: extracted memories | follow-up-memories-{ts}.yml |
Written by calling agent for extracted_memories items with treatment ∈ {queue, spawn_now} |
| Follow-up artefact: expanded branch | follow-up-expansion-{ts}.yml |
Written by calling agent for expanded_branch items with treatment ∈ {queue, spawn_now} |
| Process retrospective | retrospective-{ts}.md |
One per meditation; process analysis separate from subject-matter outputs |
| Report HTML | report-{topic-slug}-{ts}.html |
Shares {ts} with PDF pair |
| Report PDF | report-{topic-slug}-{ts}.pdf |
Shares {ts} with HTML pair |
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 63e5b52b2b47
- 2mo ago First seen · 298 lines · 0 tokens per session scan A 14c3644d499a
crux-skill-memory-meditation-coordination 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 5,422 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-coordination compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crux-skill-memory-meditation-coordinationzotoio/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 |