claude-gladiator
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
File checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollback
$ npx -y skills add Vvkmnn/claude-emporium --skill claude-vigil --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/claude-vigilContext preview
The summary Claude sees to decide when to auto-load this skill.
File checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollback
name: claude-vigil description: File checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollback triggers: [PreToolUse]
File recovery. Saves checkpoints before dangerous operations, diffs changes, restores files safely.
| 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.
| Command | Description | |---------|-------------| | `/save-vigil <name> [files]` | Create a named file checkpoint | | `/restore-vigil [name]` | Restore files from a checkpoint |
1. `vigil_save(name: "before-refactor", files: ["src/auth.ts", "src/middleware.ts"])` 2. Make changes safely 3. If something breaks: `vigil_restore(name: "before-refactor")`
1. `vigil_save(name: "before-refactor", files: [...])` 2. If **praetorian** active: also `praetorian_compact(type: "decisions", ...)` to save the reasoning 3. Make changes — both files and context are now protected 4. If something breaks:
1. `vigil_list()` — see available checkpoints 2. `vigil_diff(name: "checkpoint")` — preview what would change 3. `vigil_restore(name: "checkpoint")` — restore files 4. Optionally: `vigil_delete(name: "checkpoint")` — clean up
1. `vigil_list()` — see available checkpoints 2. `vigil_diff(name: "checkpoint")` — preview changes 3. If **historian** active: `find_file_context("filename")` to understand what changed and why 4. `vigil_restore(name: "checkpoint")` — restore files 5. If **praetorian** active: restore matching compaction for context
| 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 |
| 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 |
Content-addressable at `.claude/vigil/`. 3 named slots + 1 rotating `~quicksave`.
claude mcp add vigil -- npx claude-vigil-mcp
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Repo: Vvkmnn/claude-emporium
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
Automatic history search — checks past sessions before web research, planning, and debugging, siblings deepen coverage
Automatic tool discovery across 17 sources — hooks search before planning and after errors, siblings avoid redundant searches
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
Context preservation with cross-session memory — hooks prompt compaction at high-impact moments, siblings enrich what gets saved