recover-context

recover-context is a command for Claude Code from jameywarren/shopify-claude-quickstart. It costs 10 tokens per session (578 once invoked), scanned A, original, MIT.

A command for rebuilding project context after the conversation history has been cleared.

In plain words
What is it for?
Use it to review Git history, recent changes, project instructions, session notes, and saved project data before editing.
Why use it?
It reduces the risk of continuing work without knowing recent code changes, project instructions, or open questions.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Good fit Use it to review Git history, recent changes, project instructions, session notes, and saved project data before editing.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jameywarren/shopify-claude-quickstart/recover-context
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jameywarren/shopify-claude-quickstart

Made for: Claude Code.

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 recover-context

README.md
[![agentmods](https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/recover-context/github.svg)](https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/recover-context)
Your own site
<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/recover-context"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/recover-context/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.

agentmods 80×15 button for recover-context

Your own site · 80×15
<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/recover-context"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/recover-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 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 $0.00010 $0.00578
Opus 5 $0.00005 $0.00289
Sonnet 5 $0.00002 $0.00116
Haiku 4.5 $0.00001 $0.00058

Measured 10d ago against content hash f1eba099034b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

recover-context 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 10d 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.

.claude/commands/recover-context.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stop. Work through these steps in order before proposing anything.


Step 1 — Check git availability

git rev-parse --is-inside-work-tree 2>/dev/null && echo "git:yes" || echo "git:no"

Step 2 — Reconstruct recent history

If git is available, run both:

git log --oneline -15
git diff HEAD~1 --stat

This gives a timestamped timeline of every push and session commit, plus exactly what changed last session. Read this before touching any prose files.

If git is not available, skip to Step 3.

If both git and docs/session-log.md exist, use both — git for the timeline and exact diffs, session-log for narrative context and open questions that don't show up in diffs.


Step 3 — Re-read project state

  1. Re-read CLAUDE.md completely — store handle, active theme, current build phase
  2. Re-read docs/session-log.md if it exists — last 3 entries minimum. The most recent "Next Session: Start Here" is the first action.

Step 4 — Load store data from local snapshots

Check which of these files exist and read them. Do not re-query the API if local data is available:

  • store-data/store-profile.md — store config, installed apps, theme details
  • store-data/pages.json — all pages and handles
  • store-data/navigation.json — menu structure
  • store-data/collections.json — collection handles and rules
  • store-data/products-index.csv — product handles, titles, types, collections
  • store-data/metafield-definitions.json — defined metafields by owner type
  • store-data/theme-sections.md — section inventory

If none of these snapshots exist yet, note that and suggest running /pull-store-data after auth is confirmed.


Step 5 — Verify auth

Run /check-auth to confirm the store session is live. If auth has lapsed, re-authenticate. Do not run /init-store — that is a first-session-only command.


Step 6 — Report orientation

Tell me:

  1. What store and theme are we working on?
  2. What were we in the middle of? (from git log and/or session log)
  3. What changed last session? (from git diff or session log)
  4. What's the next concrete step?
  5. Is local store data fresh enough, or does /pull-store-data need to run?

Read the full file on GitHub · 75 lines

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. 10d ago First seen · 75 lines · 10 tokens per session scan A f1eba099034b

Subscribe to this mod's changes

recover-context is a command published in the GitHub repository jameywarren/shopify-claude-quickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 578 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.