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.
/plugin marketplace add adhenawer/claude-snapshot/plugin install snapshotWrote 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.
[](https://agentmods.dev/commands/adhenawer/claude-snapshot/inspect)<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>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.
| Model | Per session | Once 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 | $0.00025 |
Grade A, and why
inspect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/snapshot:inspect
Show the contents of a Claude Code snapshot without extracting it.
Usage
/snapshot:inspect <path-to-snapshot.tar.gz>
Steps
- Validate the path argument exists
- Run inspect via the core script:
node "${CLAUDE_PLUGIN_ROOT}/src/snapshot.mjs" inspect "$SNAPSHOT_PATH"
- 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'smethod. Iflength === 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)
- First line:
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.
- 6d ago First seen · 33 lines · 7 tokens per session scan A d26c12c1c2b3
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.
Other commands, from other repositories
chinese
A command that changes Claude Code's interface, loading messages, and spinner text to simplified Chinese.
english
Switch Claude Code back to English (UI, spinner verbs and tips).
en
Switch Claude Code back to English (short alias for /english).
zh
A short command that switches Claude Code to Simplified Chinese. It is handled locally by a command hook.
done
Finish a task - document, create PR or merge, close.
check
Quick sanity check - code (inline 6-perspective) or plan (--plan).