claude-vigil-mcp: Skill for Claude Code

.claude/skills/claude-vigil/SKILL.md

claude-vigil is a skill for Claude Code from Vvkmnn/claude-vigil-mcp. It costs 41 tokens per session (485 once invoked), scanned A, original, MIT.

A checkpoint and restore tool for risky code changes. A checkpoint is a saved project state that can be compared with or restored after refactoring, migrations, deletions, or experiments.

In plain words
What is it for?
Saving named states, comparing the current project with an earlier state, restoring a checkpoint, and deleting old checkpoints.
Why use it?
It provides a way to see what changed and recover if risky work causes problems.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Vvkmnn/claude-vigil-mcp's own configuration. It tells Claude Code how to work on claude-vigil-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-vigil-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Vvkmnn/claude-vigil-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Vvkmnn/claude-vigil-mcp/main/.claude/skills/claude-vigil/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Vvkmnn/claude-vigil-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-vigil

README.md
[![agentmods](https://agentmods.dev/badge/skills/vvkmnn/claude-vigil-mcp/claude-vigil/github.svg)](https://agentmods.dev/skills/vvkmnn/claude-vigil-mcp/claude-vigil)
Your own site
<a href="https://agentmods.dev/skills/vvkmnn/claude-vigil-mcp/claude-vigil"><img src="https://agentmods.dev/badge/skills/vvkmnn/claude-vigil-mcp/claude-vigil/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-vigil

Your own site · 80×15
<a href="https://agentmods.dev/skills/vvkmnn/claude-vigil-mcp/claude-vigil"><img src="https://agentmods.dev/badge/skills/vvkmnn/claude-vigil-mcp/claude-vigil.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00485
Opus 5 $0.00020 $0.00243
Sonnet 5 $0.00008 $0.00097
Haiku 4.5 $0.00004 $0.00049

Measured 12d ago against content hash 37f859a353e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-vigil scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/claude-vigil/SKILL.md · 51 lines

What it actually says

Claude Vigil

Checkpoint project state before risky work. Restore if things break.

When to Use

  • Before refactors, migrations, or large code changes
  • Before destructive operations (file deletions, schema changes)
  • Before experimenting with approaches you might revert
  • Before rm, mv, sed -i, git checkout, git reset
  • When the user asks to "save state" or "checkpoint"

Quick Reference

Tool Purpose
vigil_save Create named checkpoint — background, returns in <5ms
vigil_list Show all checkpoints with disk usage
vigil_diff Compare current state to a checkpoint
vigil_restore Revert to checkpoint — quicksaves current state first, preserves displaced files
vigil_delete Remove a checkpoint and reclaim space

Workflow

  1. vigil_save(name: "before-refactor") — first save auto-detects derived dirs from .gitignore
  2. Make the risky changes
  3. vigil_diff(name: "before-refactor") — check what changed
  4. If broken: vigil_restore(name: "before-refactor") — then rebuild derived dirs
  5. If good: vigil_delete(name: "before-refactor") — reclaim space

After Restore

Vigil skips derived directories (node_modules, dist, target, venv). Read the output — it lists what needs rebuilding. Run the project's install and build commands.

Slot Management

Default: 3 checkpoint slots. When full, delete old checkpoints or increase capacity via max_checkpoints parameter.

Common Mistakes

Mistake Fix
Forgetting to rebuild after restore Read vigil's output — it lists what needs rebuilding
Restoring without checking diff first Use vigil_diff to see what will change
Not saving before destructive bash Save before rm, mv, sed -i, git checkout, git reset
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 51 lines · 41 tokens per session scan A 37f859a353e6

Subscribe to this mod's changes

claude-vigil is a skill published in the GitHub repository Vvkmnn/claude-vigil-mcp (7 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 485 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.