ReddRadar
Agent skill
claude-vigil
File checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollback
Install this agent skill to your Project
npx add-skill https://github.com/Vvkmnn/claude-emporium/tree/main/plugins/claude-vigil/skills/claude-vigil
SKILL.md
Vigil Plugin
File recovery. Saves checkpoints before dangerous operations, diffs changes, restores files safely.
Hooks
| Hook | When | Action |
|---|---|---|
| PreToolUse(Bash) | Destructive command detected | Auto-quicksaves affected files (rm, mv, git reset, etc.) |
Token cost: 0 on safe commands, ~30-50 on destructive. The regex matches: rm, rmdir, mv, sed -i, perl -i, git checkout/reset/clean/restore, output redirects.
Commands
| Command | Description |
|---|---|
/save-vigil <name> [files] |
Create a named file checkpoint |
/restore-vigil [name] |
Restore files from a checkpoint |
Workflows
Checkpoint (standalone)
vigil_save(name: "before-refactor", files: ["src/auth.ts", "src/middleware.ts"])- Make changes safely
- If something breaks:
vigil_restore(name: "before-refactor")
Checkpoint (with siblings)
vigil_save(name: "before-refactor", files: [...])- If praetorian active: also
praetorian_compact(type: "decisions", ...)to save the reasoning - Make changes — both files and context are now protected
- If something breaks:
vigil_restore(name: "before-refactor")— restore filespraetorian_restore("before-refactor")— restore context
Recovery (standalone)
vigil_list()— see available checkpointsvigil_diff(name: "checkpoint")— preview what would changevigil_restore(name: "checkpoint")— restore files- Optionally:
vigil_delete(name: "checkpoint")— clean up
Recovery (with siblings)
vigil_list()— see available checkpointsvigil_diff(name: "checkpoint")— preview changes- If historian active:
find_file_context("filename")to understand what changed and why vigil_restore(name: "checkpoint")— restore files- If praetorian active: restore matching compaction for context
Sibling Synergy
| Sibling | Value | How |
|---|---|---|
| Praetorian | Context saved alongside files | Pair vigil checkpoints with praetorian compactions for full state recovery |
| Historian | File change context from history | find_file_context() explains what happened between checkpoint and now |
MCP Tools Reference
| Tool | Purpose |
|---|---|
vigil_save |
Create named checkpoint (SHA-256 + gzip dedup) |
vigil_list |
List available checkpoints with metadata |
vigil_diff |
Preview changes since checkpoint |
vigil_restore |
Restore files from checkpoint |
vigil_delete |
Remove a checkpoint and free storage |
Storage
Content-addressable at .claude/vigil/. 3 named slots + 1 rotating ~quicksave.
Requires
claude mcp add vigil -- npx claude-vigil-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-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-praetorian
Context preservation with cross-session memory — hooks prompt compaction at high-impact moments, siblings enrich what gets saved
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?