inspect

inspect is a command for Claude Code from adhenawer/claude-snapshot. It costs 7 tokens per session (250 once invoked), scanned A, original, MIT.

A command for previewing the contents of a Claude Code snapshot, which is a compressed record of configuration and installed add-ons. It reads the snapshot without unpacking its files.

In plain words
What is it for?
Use it to inspect snapshot manifests, list included MCP servers and plugins, check marketplace registrations, and see export details.
Why use it?
It lets you check what a snapshot contains before extracting or restoring it. This helps verify plugins, servers, hooks, files, versions, and snapshot type safely.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the snapshot plugin — 4 commands shipped together

Good fit Use it to inspect snapshot manifests, list included MCP servers and plugins…

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add adhenawer/claude-snapshot
Claude Code
/plugin install snapshot

Made for: Claude Code.

Or install snapshot, the plugin that ships this one along with the rest of its 4 commands.

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 inspect

README.md
[![agentmods](https://agentmods.dev/badge/commands/adhenawer/claude-snapshot/inspect.svg)](https://agentmods.dev/commands/adhenawer/claude-snapshot/inspect)
Your own site
<a href="https://agentmods.dev/commands/adhenawer/claude-snapshot/inspect"><img src="https://agentmods.dev/badge/commands/adhenawer/claude-snapshot/inspect.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 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 $0.00007 $0.00250
Opus 5 $0.00003 $0.00125
Sonnet 5 $0.00001 $0.00050
Haiku 4.5 $0.00001 $0.00025

Measured 6d ago against content hash d26c12c1c2b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

inspect 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 6d 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.

commands/inspect.md · 33 lines

What it actually says

/snapshot:inspect

Show the contents of a Claude Code snapshot without extracting it.

Usage

/snapshot:inspect <path-to-snapshot.tar.gz>

Steps

  1. Validate the path argument exists
  2. Run inspect via the core script:
node "${CLAUDE_PLUGIN_ROOT}/src/snapshot.mjs" inspect "$SNAPSHOT_PATH"
  1. Parse the JSON manifest and present a readable summary:
    • First line: Schema {manifest.schemaVersion} (e.g. Schema 1.0.0)
    • If manifest.mcpServers.length > 0, show a line: MCP servers: N (npm: X, pip: Y, binary: Z, manual: W) — counts grouped by each server's method. If length === 0, omit the line entirely.
    • Export date and source machine
    • Plugin list with versions
    • Marketplace registrations
    • Hook scripts
    • Global MD files
    • Whether it's a slim or full snapshot (check if manifest mentions cache entries)
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. 6d ago First seen · 33 lines · 7 tokens per session scan A d26c12c1c2b3

Subscribe to this mod's changes

inspect is a command published in the GitHub repository adhenawer/claude-snapshot (2 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 250 once invoked, about $0.0000 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.