CRUX-Compress: Skill for Cursor

.cursor/skills/crux-skill-memory-meditation-coordination/SKILL.md

crux-skill-memory-meditation-coordination is a skill for Cursor from zotoio/CRUX-Compress. It costs 0 tokens per session (5,425 once invoked), scanned A, original, MIT.

A file-naming and coordination guide for CRUX memory meditation, a process that explores and consolidates stored memories. It defines how working files, reports, placeholders, and branch results are named and found.

In plain words
What is it for?
Use it when reading, writing, linking, or polling for meditation files, including branch outputs, reports, facets, indexes, and process retrospectives. It is a shared utility used by the other meditation procedures.
Why use it?
It prevents agents working on the same meditation task from losing track of files or using inconsistent names. It also provides rules for checking whether expected files have appeared.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is zotoio/CRUX-Compress's own configuration. It tells 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/skills/crux-skill-memory-meditation-coordination/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zotoio/CRUX-Compress

Made for: 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-skill-memory-meditation-coordination

README.md
[![agentmods](https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-coordination/github.svg)](https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-meditation-coordination)
Your own site
<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.

agentmods 80×15 button for crux-skill-memory-meditation-coordination

Your own site · 80×15
<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>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,425 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.05425
Opus 5 $0.00000 $0.02712
Sonnet 5 $0.00000 $0.01085
Haiku 4.5 $0.00000 $0.00543

Measured 12d ago against content hash 14c3644d499a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 12d 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/skills/crux-skill-memory-meditation-coordination/SKILL.md · 298 lines

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

Read the full file on GitHub · 298 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. 12d ago First seen · 298 lines · 0 tokens per session scan A 14c3644d499a

Subscribe to this mod's changes

crux-skill-memory-meditation-coordination is a skill published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,425 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.

Related

Other skills, from other repositories

simplemem-skill

Store and retrieve conversation memories across sessions. Use when asked to 'remember this', 'save conversation', 'add to memory', 'what did we discuss about...', 'query memories', or 'import chat history'. Also use proactively to preserve important dialogue context and decisions.

aiming-lab/SimpleMem · 58 tokens

[object Object]

Read, search, and open notes in the user's "{{GRAPHNAME}}" Reflect graph via the reflect CLI. Use when the user asks about their notes, daily notes, journal, or anything they may have written down in Reflect.

team-reflect/reflect-open · 51 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

init

Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.

grpcer/ownmem · 43 tokens

daily-journal

A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say…

huytieu/COG-second-brain · 107 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens