AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Vault Concepts

skill-markphelps-agent-plugins-vault-concepts · by markphelps

Maintain canonical concept pages and surface recurring themes

— No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-markphelps-agent-plugins-vault-concepts

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-markphelps-agent-plugins-vault-concepts)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Vault Concepts? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Concepts

Promote recurring themes into canonical concept pages and keep concept navigation coherent.

Portent reference: ../references/portent-knowledge-base-spec.md.

Recency Priority

Work the active surface newest-first, ranked by each object's updated frontmatter date (fall back to file modification time when updated is absent). Concentrate scrutiny on the freshest material — recently-touched objects are where active thinking lives and where new mismatches, overlaps, and gaps appear. Long-untouched objects are assumed settled and rank lower, but are never excluded: they remain valid link targets, merge destinations, and canonical homes, and still get a structural check (broken links, orphaning).

Weight theme detection toward recent notes so emerging themes surface early, but keep temporal spread as the high-confidence signal: a concept still needs occurrences across time, not just a recent burst.

Purpose

Maintain notes/concepts/ as the durable vocabulary of your vault. Surface cross-domain patterns and decide when transience deserves permanence.

Concept pages are Portent Topic objects. New recurring-theme pages should use type: Topic, status: organized, and explicit related_to links to the Projects, Notes, Events, or Responsibilities they help explain.

Parameters

  • --topic TOPIC focus on specific theme (optional)
  • --mode report|apply (default: report)

Thresholds for New Concept Creation

Only create new concept pages when ALL are true:

  • Theme appears in 3+ unrelated notes
  • Evidence is concrete and linkable
  • Destination concept is clear
  • Destination Topic object is clear
  • Change is additive and low-risk

Workflow

  1. Scan: Read active surface (notes/, ideas/, projects/) for recurring

themes

  1. Detect: Extract patterns across unrelated notes:
  • Phrases/metaphors that recur
  • Principles or mental models
  • Unresolved questions with traction
  1. Filter: Remove false positives:
  • Deliberate tag repetition
  • Common filler phrasing
  • Same-project-only repetition
  1. Cluster: Group related patterns and rank by confidence
  2. Decide per candidate:
  • Update existing concept page
  • Merge near-duplicate concept pages into one canonical concept
  • Create new concept page (if thresholds met)
  • Defer (insufficient evidence)
  1. Normalize: Rewrite transient note references to point to canonical

concepts

  1. Refresh: Update index.md when concept navigation changes
  2. Log: Append concise operation entry

Confidence Rubric

  • High: 3+ unrelated notes with temporal spread
  • Medium: 2 unrelated notes with strong conceptual overlap
  • Low: Weak recurrence or same-domain concentration

Apply Behavior

  • report: List candidates only, no changes
  • apply: Update existing concepts; merge high-confidence duplicates; create

new ones when thresholds met

Merge Rules

Merge concept pages when they name the same principle, mental model, or durable vocabulary item. Do not merge broad neighboring concepts just because they are often linked together.

  • Choose the clearest, most established page as canonical.
  • Preserve distinct examples, open questions, and source links from merged

pages.

  • Rewrite links from merged pages to the canonical concept.
  • Keep aliases when alternate names are likely search terms.
  • Report medium-confidence concept overlaps instead of merging them.

Safety

  • Prefer updating existing concepts over creating near-duplicates
  • Never delete notes or archive content
  • Never merge concept pages that represent different decisions or levels of

abstraction

  • Never modify raw/, processed/, or assets/
  • Confirm before creating new concept pages

Output

Return:

  • Concepts created/updated/proposed (with confidence)
  • Concepts merged/proposed for merge
  • Topic object metadata added or updated
  • Evidence links used
  • Reference normalization performed
  • Index/log update status
  • Recommended follow-up actions

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.