Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/adhenawer/claude-snapshot/diffgit clone --depth 1 https://github.com/adhenawer/claude-snapshotWhat 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 | $0.00011 | $0.00390 |
| Opus 5 | $0.00005 | $0.00195 |
| Sonnet 5 | $0.00002 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
diff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/snapshot:diff
Compare a Claude Code snapshot against your current local setup. Shows what would change if you applied it.
Usage
/snapshot:diff <path-to-snapshot.tar.gz>
Steps
- Validate the path argument exists
- Run diff via the core script:
node "${CLAUDE_PLUGIN_ROOT}/src/snapshot.mjs" diff "$SNAPSHOT_PATH"
- Parse the JSON diff result and present as a readable report:
Format:
Plugins:
+ plugin-name@version (missing locally)
~ plugin-name local -> snapshot (version mismatch)
= plugin-name@version (match)
Hooks:
+ hook-name.sh (missing locally)
= hook-name.sh (match)
Global MDs:
+ NEWFILE.md (missing locally)
~ CLAUDE.md (content differs)
= RTK.md (match)
Settings:
~ settings.json (content differs)
= settings.json (match)
MCP servers:
+ MCP: server-name (npm) (missing locally)
= 3 MCP servers already present.
Use + for additions, ~ for changes, = for matches.
MCP servers rendering:
- If
diff.mcpServers.added.length > 0, render each as+ MCP: {name} ({method}), followed by the note: "These MCP servers are in the snapshot but not on this machine. Apply will tell you how to install each." - If
diff.mcpServers.matched.length > 0andaddedis empty, render a single line:= {N} MCP servers already present.
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.
- 2d ago First seen · 56 lines · 11 tokens per session scan A 70ebcadb9124
diff is a command published in the GitHub repository adhenawer/claude-snapshot (2 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 390 once invoked, about $0.0001 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
icon-lookup
Search for icons by name, or identify a PUA character.
ssh-keys
Manage SSH keys across hosts — generate, sync, list status, or delete.
pr-review
Intelligent PR code review with dynamic agent allocation based on change types.
release
Release and versioning commands.
cleanup
Sweep /.claude disk hygiene to stated retentions, clean up stale plans from repos, audit plugin health, and compact agent memory files.
cost-estimate
Estimate development cost of a codebase based on lines of code and complexity.