Skip to content
Agentmart
Submit a tool

grocery-staging

Detect protein deficits and stage high-protein groceries with mandatory approval before checkout.

Skill by Mohit5Upadhyay

IndexedMIT
Write a review

Chalk Labs

Need help deploying grocery-staging?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mohit5upadhyay-grocery-staging

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Detect protein deficits and stage high-protein groceries with mandatory approval before checkout.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/grocery-staging

What's inside

Skill name
grocery-staging
Description
Detect protein deficits and stage high-protein groceries with mandatory approval before checkout.
License
MIT
Instructions
74 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Grocery Staging

Proactively detect protein deficits and stage recommended high-protein items in user's grocery cart.

## Deficit Detection

Monitor weekly protein intake vs. target. If user is consistently falling short:

```sh
python3 "$HERMES_HOME/skills/meal-logging/scripts/log_meal.py" summary-today
python3 "$HERMES_HOME/skills/metabolix-profile/scripts/profile.py" targets
```

Trigger staging when:
- 3+ consecutive days below 85% protein target
- Weekly average < 90% protein target

## High-Protein Recommendations

Common items to stage:
- Greek Yogurt (Fage Total 0%, 500g): ~18g protein
- Whey Protein Isolate (Optimum Nutrition, 2lb): ~24g per scoop
- Chicken Breast (boneless, 1kg): ~30g per 100g
- Cottage Cheese (low-fat, 500g): ~12g per 100g
- Eggs (dozen): ~6g per egg

## Staging Workflow via Latch

**CRITICAL**: Only stage items. NEVER execute final payment without explicit "CONFIRM BUY" approval.

1. **Open Grocery Service**: Use Latch browser to navigate to Amazon Fresh (or configured service)
2. **Search & Add**: Search for recommended items, add to cart
3. **Navigate to Checkout**: Go to cart review page, DO NOT proceed to payment
4. **Send Approval Request** via Plow Chat:
   ```
   ⚠️ Protein deficit detected (3 days < target).
   
   Staged in Amazon cart:
   - 2x Fage Greek Yogurt 0% (500g) - $6.98 each
   - 1x Optimum Whey Isolate (2lb) - $39.99
   
   Total: $53.95 (before tax)
   
   Items ready for checkout. Reply 'CONFIRM BUY' to complete purchase.
   ```

5. **Wait for Approval**: Do NOT click "Place Order" or final payment button
6. **On "CONFIRM BUY" Response**: Execute final payment click, verify order confirmation, send receipt screenshot

## Approval Gate

Absolutely **FORBIDDEN** to execute payment without exact phrase "CONFIRM BUY" from user.

Any other response:
- "CANCEL": Remove items from cart, confirm cancellation
- "CHANGE": Ask what to modify, update cart, re-request approval
- No response after 24h: Send reminder, do NOT auto-purchase

## Post-Purchase

After successful order:
1. Screenshot order confirmation
2. Note order number and delivery date
3. Send confirmation SMS with screenshot
4. Update grocery staging log to prevent duplicate staging

## Error Handling

- If grocery service unavailable: Report, suggest manual order
- If items out of stock: Suggest alternatives, re-request approval
- If payment fails: Report error, do NOT retry without user instruction
- If cart was cleared: Re-stage and re-request approval

From Mohit5Upadhyay/metabolix, MIT.

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Sep 14, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Mohit5Upadhyay

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get grocery-staging running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying grocery-staging?

CallGet help
Cite this page

grocery-staging skill. Agent Mart. https://agentmart.dev/skills/mohit5upadhyay-grocery-staging (last updated 2026-10-24)