Doordash Report
Spend and activity report for agent-driven DoorDash ordering - reconciles the audit log against real order history and renders totals, per-restaurant breakdown, repeat rate, and abandoned-cart rate
$ npx claude-code-templates@latest --command="doordash/doordash-report" --yesRequires Claude Code. The command adds this command to your project's .claudedirectory — nothing runs on ToolZip's servers.
What's inside this command
Component source
DoorDash Activity Report
Report period: $ARGUMENTS (default: week)
Data sources: ~/.claude/dd-guard/audit.jsonl (written by the doordash-audit-log
hook), ~/.claude/dd-guard/ledger.jsonl (if doordash-spend-guard is installed),
and live dd-cli order history.
Current State
- Audit events: !
wc -l < ~/.claude/dd-guard/audit.jsonl 2>/dev/null || echo "0" - Last reconciled: !
cat ~/.claude/dd-guard/last-reconciled 2>/dev/null || echo "(never)"
Task
1. Reconcile
- Run
dd-cli order historyand parse the entries (date, restaurant,
- Parsing fallback: the exact output format is version-dependent. If
you cannot parse it confidently, fall back to intent-only mode:
report from the audit log alone and label the report clearly as
"unreconciled — based on agent activity, not confirmed orders".
- Match
checkout_urlaudit events (and ledger intents) against history
- matched → confirmed order
- checkout_url event with no matching order after 24h → abandoned cart
- Update
~/.claude/dd-guard/last-reconciledwith today's date. If
paid /
abandoned exactly as /doordash-budget reconcile would.
2. Render the report (right-sized — no dashboard theater)
DoorDash activity — week of 2026-07-13
Confirmed spend: $87.40 (prev week $52.10, +68%)
Orders: 4 confirmed, 1 abandoned cart (20% abandon rate)
By restaurant: Sweetgreen $34.90 (2x) · Thai Palace $28.50 · ...
Repeat rate: 75% of orders were reorders/playbooks
Agent activity: 12 searches, 9 cart mutations, 5 checkout URLs
- Totals from history are real; totals from intents are pre-fee subtotals —
monthargument widens the window to 30 days and adds a week-by-week
3. Answer follow-ups from data
For questions like "what did I order most?" or "how much on ramen this
month?", query the audit log with jq (the doordash-order-ledger skill documents
recipes) — never answer from memory.
Rules
- Never edit audit.jsonl — it is append-only; only the hook writes it.
- Keep
cuisine-map.json(restaurant → cuisine) next to the audit log if
- Privacy: these files are a local plaintext record of eating habits.
~/.claude/dd-guard/ out of any repo.Related Claude Code Commands
Doordash Budget
View DoorDash spend vs caps, edit the dd-guard spending policy interactively, and reconcile the intent ledger against real order history
Doordash Lunch
Team lunch orchestration via DoorDash CLI - build a group round, emit checkout with split table, track payer rotation
Doordash Playbook
Manage saved DoorDash order playbooks (list, add from order history, remove, inspect) stored in ~/.claude/dd-cli/playbooks.json
Doordash Profile
Manage the dietary profile (allergens with severity tiers, diets, dislikes) used by doordash-allergy-shield to vet DoorDash carts
Generate Tests
Generate a complete test file for a specified source file or component. Use when the user explicitly asks to write, create, or generate tests for a specific file.
Ultra Think
Multi-framework structured analysis: surfaces hidden assumptions, generates competing solutions, stress-tests each with adversarial reasoning, and delivers confidence-calibrated recommendations
Catalog data and component content are sourced from the open-source davila7/claude-code-templates project (MIT license). ToolZip curates the listing and writes original descriptions; every component links back to its original source. Claude Code is a product of Anthropic. ToolZip is an independent catalog and is not affiliated with or endorsed by Anthropic.