ReddRadar
Agent skill
claude-praetorian
Context preservation with cross-session memory — hooks prompt compaction at high-impact moments, siblings enrich what gets saved
Install this agent skill to your Project
npx add-skill https://github.com/Vvkmnn/claude-emporium/tree/main/plugins/claude-praetorian/skills/claude-praetorian
SKILL.md
Praetorian Plugin
Context guard. Saves and restores valuable context at the right moments — before planning, after research, when subagents complete.
Hooks
| Hook | When | Action |
|---|---|---|
| PreToolUse(EnterPlanMode) | Before planning | Lists prior compactions, suggests restoring |
| PreCompact | Before context resets | Prompts to save decisions/insights/findings |
| PostToolUse(WebFetch/WebSearch) | After web research | Prompts to compact as web_research |
| SubagentStop | After subagent completes | Prompts to compact as task_result |
Commands
| Command | Description |
|---|---|
/compact-praetorian [type] [title] |
Save current context |
/restore-praetorian [query] |
Load previous context |
Workflows
Compact (standalone)
- Identify what's worth saving (research, decisions, patterns)
praetorian_compact(type, title, key_insights, refs)- Verify with
praetorian_restore(title)to confirm it saved
Compact (with siblings)
- If historian active:
search_plans()to check if past context already covers this - If oracle active: include any tool discoveries in
key_insights praetorian_compact(type, title, key_insights, refs)- If vigil active: files are also checkpointed via quicksave
Restore (standalone)
praetorian_restore()— list recent compactionspraetorian_restore("query")— search for specific topic- Summarize findings for the current task
Restore (with siblings)
praetorian_restore("query")— load praetorian context- If historian active:
search_conversations("query")for broader session history - If oracle active:
search("query")for tools relevant to the restored context - Combine all sources into a unified briefing
Sibling Synergy
| Sibling | Value | How |
|---|---|---|
| Historian | Past plans surface during planning compactions | search_plans() enriches pre-plan hook |
| Oracle | Tool discoveries included in compactions | Oracle results added to key_insights |
| Gladiator | Observations inform what to compact | Failure patterns highlight important context |
| Vigil | Files checkpointed alongside context | Quicksave protects files during compaction |
Requires
claude mcp add praetorian -- npx claude-praetorian-mcp
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
Vvkmnn/claude-emporium
claude-orator
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
Vvkmnn/claude-emporium
claude-vigil
File checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollback
Vvkmnn/claude-emporium
claude-historian
Automatic history search — checks past sessions before web research, planning, and debugging, siblings deepen coverage
Vvkmnn/claude-emporium
claude-oracle
Automatic tool discovery across 17 sources — hooks search before planning and after errors, siblings avoid redundant searches
Vvkmnn/claude-emporium
claude-gladiator
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
Didn't find tool you were looking for?