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

Hydrate

skill-robabby-claude-skills-hydrate · by robabby

Load context from Obsidian memory system at session start

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-robabby-claude-skills-hydrate

✓ 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-robabby-claude-skills-hydrate)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
6mo 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 Hydrate? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Hydrate

Load context from the Obsidian memory system for session continuity.

Workflow

  1. Read the living context documents:
  • Areas/AI/Context/Current State.md - Current situation, priorities, blockers
  • Areas/AI/Context/Decision Register.md - Pending decisions
  1. If $ARGUMENTS provided (topic/project), search for relevant memories:

`` Grep pattern="$TOPIC" path="/Areas/AI/Memory" glob="*.md" `` Read top 5-10 matching memory files by importance

  1. If no arguments, get recent memories:

`` Glob pattern="Areas/AI/Memory/**/*.md" path="" `` Read 5-10 most recent memory files

  1. Scan recent session logs for continuity:

`` Glob pattern="Areas/AI/Collaboration/Sessions/*.md" path="" `` Read 2-3 most recent sessions

  1. Internalize the context silently - don't recite it back verbatim
  1. Acknowledge briefly:
  • Key context points from Current State
  • Number of memories loaded
  • Recent session topics
  • Ready to proceed

Context Sources

| Source | Path | Purpose | |--------|------|---------| | Current State | Areas/AI/Context/Current State.md | Life situation, priorities, blockers | | Decision Register | Areas/AI/Context/Decision Register.md | Pending decisions | | Memories | Areas/AI/Memory/**/*.md | Persistent cross-session knowledge | | Sessions | Areas/AI/Collaboration/Sessions/*.md | Recent session continuity |

Examples

User: /hydrate -> Load Current State, recent memories, recent sessions -> "Loaded context: Current State shows interview prep priority. 8 recent memories loaded. Last session covered statusline config. Ready."

User: /hydrate metatron -> Load Current State + search memories for "metatron" -> "Loaded context: Found 5 memories about Metatron (deployment, stack decisions, design). Current priority is interview prep. Ready."

User: /hydrate robabby -> Load Current State + search memories for "robabby" -> "Loaded context: Found 7 memories about robabby.com (sacred geometry redesign, PRs, patterns learned). Ready."

Response Format

Brief acknowledgment:

  • Context loaded (Current State key points if relevant)
  • Number of memories found
  • Recent session topics if applicable
  • "Ready to proceed" or similar

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.