Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Data-Wise/craftnpx agentmods add commands/data-wise/craft/restoreWrote 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/data-wise/craft/restore)<a href="https://agentmods.dev/commands/data-wise/craft/restore"><img src="https://agentmods.dev/badge/commands/data-wise/craft/restore/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.
<a href="https://agentmods.dev/commands/data-wise/craft/restore"><img src="https://agentmods.dev/badge/commands/data-wise/craft/restore.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00008 | $0.00670 |
| Opus 5.5 | $0.00003 | $0.00268 |
| Sonnet 5.5 | $0.00002 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/restore - Restore Git & Session Context
This command is a thin shim. The canonical behavior lives in two skills: git-activity recap (
dev/gitskill, Operation 7) and.STATUS-based session recap (adhd-workflowskill, §2 "Context Restoration"). This file exists to give both a single, discoverable combined entry point — seedocs/specs/SPEC-craft-restore-2026-07-17.md.
Usage
/craft:restore # default mode
/craft:restore detailed # full verbosity on the git-activity portion
/craft:restore summary # minimal verbosity on the git-activity portion
When invoked
- Session state: run the
adhd-workflowskill's §2 "Context Restoration (recap)" operation —.STATUSstate, git activity (last 48h), open PRs/issues, planning files, Obsidian flow status. This is single-verbosity; the mode argument does not change it. - Git activity: run the
dev/gitskill's Operation 7 (git activity recap) — today's/this week's commits, branch ahead/behind, unpushed work, open PRs — using whichever mode (default|detailed|summary) was passed. - De-dupe on presentation, not on source logic: both operations independently
surface recent commits and open PRs. Present one combined git-activity block
(from step 2, mode-aware) rather than printing the same commits/PRs twice.
Session-only content from step 1 (
.STATUSnext-action/blockers, planning files, Obsidian flow status) goes in its own section. - Present as one combined, ADHD-friendly summary: git state first, session state second, a single "what's next" line last.
- Do not reimplement either operation here. Any change to git-recap logic
belongs in
dev/git; any change to session-recap logic belongs inadhd-workflow. This file is routing only.
Read-only
/craft:restore never writes .STATUS, never commits, never syncs anything — it
only reads and reports. There is no --sync flag (unlike savant:restore, which
optionally applies diff-gated doc updates). If write-back is ever wanted, that is
a separate, explicitly-scoped addition — not part of this command today.
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.
- 1mo ago First seen · 54 lines · 8 tokens per session scan A a1eb807984e7
restore is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 7d ago), licensed MIT. It adds 8 tokens to every session and 670 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
design-ship
One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
issue-to-mr-setup
Create an automation that implements GitLab issues when a configurable trigger label is applied. Polls one or more projects deterministically, clones the default branch, starts one OpenHands conversation per label event, then commits, pushes, and opens the merge request itself.
validate-pr-description
Use when validating a PR title and description for conventional commit format, issue linking keywords, and template compliance before submission.
deploy
Run the complete ClawBridge release process. This is the ONLY way to deploy — follow every step.
run-plan
Execute implementation plan phases for a change.