DoorDash Order Ledger
SkillDocs & knowledgedoordash-order-ledger is a skill that adds an accountability layer to agent-driven DoorDash ordering. It works with the doordash-audit-log hook, which appends every dd-cli invocation to an append-only audit log, and with the /doordash-report command, so questions about what has been ordered and what it cost can be answered from data instead of memory.
Use DoorDash Order Ledger in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add DoorDash Order Ledger and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the DoorDash Order Ledger skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Have dd-cli available so DoorDash ordering activity can be recorded.
What your AI can do with it
- Tracks DoorDash orders placed through dd-cli by an agent
- Works with the doordash-audit-log hook to keep an append-only audit log of every dd-cli
- Answers what has been ordered and what it cost from recorded data
- Pairs with the /doordash-report command to produce order and cost reports
Getting started
- Have dd-cli available so DoorDash ordering activity can be recorded.
- Set up the doordash-audit-log hook so every dd-cli invocation is appended to an append-only audit log.
- Add the doordash-order-ledger skill to the agent.
- Use the /doordash-report command to ask what has been ordered and what it cost.
What this skill tells your AI
The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/doordash/doordash-order-ledger/SKILL.md and read by ahel’s review.
Every dd-cli command the agent runs is recorded by the doordash-audit-log hook
in ~/.claude/dd-guard/audit.jsonl — one versioned JSON line per event.
This skill teaches you to answer questions from that log instead of
guessing.
Install the bundle: hook
doordash/doordash-audit-log(the recorder), command/doordash-report(reconciled summaries), this skill (querying). Composes with doordash-spend-guard (shares the~/.claude/dd-guard/state directory) but runs standalone.
Line schema (v1)
{
"v": 1,
"ts": "2026-07-19T13:02:11",
"session_id": "abc123",
"cwd": "/Users/x/project",
"command": "dd-cli search --query \"ramen near me\"",
"event_type": "search | cart_mutation | checkout_url | history | login | other",
"cart_uuid": "…or null",
"order_uuid": "…or null",
"exit_ok": true
}
Commands are secret-stripped before persisting and truncated to 500 chars.
The v field guards future schema changes — check it before assuming
fields.
Query recipes (jq)
Answer from data, not memory:
# What did the agent do today?
jq -r 'select(.ts >= "2026-07-19") | "\(.ts) \(.event_type) \(.command)"' ~/.claude/dd-guard/audit.jsonl
# Checkout URLs issued this week (intents, not confirmed orders)
jq -r 'select(.event_type == "checkout_url" and .ts >= "2026-07-13")' ~/.claude/dd-guard/audit.jsonl
# Activity by type
jq -s 'group_by(.event_type) | map({type: .[0].event_type, n: length})' ~/.claude/dd-guard/audit.jsonl
# Which sessions touched carts?
jq -r 'select(.event_type == "cart_mutation") | .session_id' ~/.claude/dd-guard/audit.jsonl | sort | uniq -c
# Failed dd-cli calls (agent flailing?)
jq -r 'select(.exit_ok == false) | "\(.ts) \(.command)"' ~/.claude/dd-guard/audit.jsonl
When the user asks a money question ("how much this week?"), prefer
/doordash-report — it reconciles against real dd-cli order history and labels
intent-only numbers honestly. Raw checkout_url counts are intents: the
human may have abandoned the payment page.
Honest semantics
- checkout_url ≠ purchase. It records that a link was issued. Only
reconciliation against
order historyconfirms money moved. - Subtotals (when present via doordash-spend-guard's ledger) are pre-fee.
- The log records what went through Claude Code's Bash tool — orders placed by the human directly in a terminal or app are invisible to it.
Maintenance
- Rotation: when audit.jsonl exceeds ~5 MB, rotate:
mv audit.jsonl audit-$(date +%Y%m).jsonl && gzip audit-*.jsonl(keep the gzips; they are the history). - Never edit lines — append-only is the audit property. Corrections go in reports, not in the log.
- Privacy: this is a plaintext record of eating habits and schedules.
Keep
~/.claude/dd-guard/out of repos and backups you share. Mention this to the user the first time you query the log in a session.
Signals
- GitHub stars
- 32k
- Forks
- 4k
- Last commit
- Oct 2026
Questions
- What has my AI been ordering and what did it cost?
- The skill answers this from the append-only audit log written by the doordash-audit-log hook, using the /doordash-report command, rather than relying on the agent's memory.
- How does it record ordering activity?
- The doordash-audit-log hook appends every dd-cli invocation to an append-only audit log, which the skill uses as its source of data.
- Can it change or delete past log entries?
- No. The audit log is append-only, so entries are added, not edited or removed.
Advanced
- Item type
- skill
- Key
doordash-order-ledger- Source
- github.com/davila7/claude-code-templates
github.com/davila7/claude-code-templates
More in Docs & knowledge
Skill · mattpocock
More in Docs & knowledgecanvas-design
Skill · anthropics
More in Docs & knowledgedoc-coauthoring
Skill · anthropics
More in Docs & knowledgewriting-for-agents
Skill · mattpocock
More in Docs & knowledgespec-driven-development
Skill · addyosmani
More in Docs & knowledgedefuddle
Skill · kepano
More in Docs & knowledge