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/cwakim/claude-plugins/restoregit clone --depth 1 https://github.com/cwakim/claude-pluginsWhat 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 | $0.00064 | $0.01697 |
| Opus 5 | $0.00032 | $0.00848 |
| Sonnet 5 | $0.00013 | $0.00339 |
| Haiku 4.5 | $0.00006 | $0.00170 |
Grade A, and why
restore 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Restore (restore [--dry-run] [path])
Copies from a backup source back onto this machine. Interactive and
conservative: it adds and (only with consent) overwrites, and it never
deletes anything that exists only locally. Whichever source resolves
below, restore only ever reads from it: it never writes back to the
source, and never pushes anywhere. With --dry-run it goes exactly as far
as the plan (step 3) and stops: nothing is applied, no question is asked,
and any temp extraction directory is cleaned up. Useful for checking what a
restore would do, especially against the GitHub mirror, which may be weeks
ahead of or behind this machine.
The mirror tree and the name-to-target derivation rules live in
${CLAUDE_PLUGIN_ROOT}/docs/layout.md; read it before building the plan.
To converge this machine with a different machine's mirror, use merge
(${CLAUDE_PLUGIN_ROOT}/commands/merge.md) instead: restore maps a mirror
back onto the machine it came from (or a replacement for it), merge
reconciles two machines' divergent state.
Resolve the source
<path>given: a zip made byzip <path>, or its already-extracted folder. If<path>is a file (a.zip), extract it into a fresh temp directory (mktemp -d) and use that as the source root; if it is already a directory, use it directly. Verify the source root contains at least onemachines/<hostname>/subtree; if not, say so and stop. No GitHub involved at all: no clone, nogh, no network, and no need for/backup setupto have ever run.- No
<path>: a configured backup target. Two kinds can be configured, and both may be at once (seedocs/object-storage.md):- GitHub mirror (
~/.claude/memory-backup/is a clone with an origin). If it is not configured, this is probably the disaster-recovery path: ask for the backup repo (owner/name), verify it exists, and clone it into place first. Otherwisegit pull --ff-onlyso the mirror is current. The source root is the clone. - Object storage (
~/.claude/memory-backup-obstore.jsonexists). Read bucket/prefix/endpoint/region/profile from it and materialize the mirror into a fresh temp directory (mktemp -d) with${CLAUDE_PLUGIN_ROOT}/scripts/obstore-pull.sh --dest <tmp> --bucket .... That temp directory is then the source root, handled exactly like an extracted zip: read-only, and cleaned up at the end (step 4) or on any early stop, since this run created it. - Both configured: ask via
AskUserQuestionwhich to restore from (they can differ: the bucket may be ahead of or behind the git mirror). Only one configured: use it without asking.
- GitHub mirror (
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.
- yesterday First seen · 118 lines · 64 tokens per session scan A f59cea8b7e6f
restore is a command published in the GitHub repository cwakim/claude-plugins (2 stars, last pushed 11d ago), licensed MIT. It adds 64 tokens to every session and 1,697 once invoked, about $0.0003 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.