What it does
The skill 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. Together they let a user check what their AI agent has ordered and what it cost by querying recorded data rather than relying on memory. The skill covers the log schema, query patterns, log rotation and privacy guidance, including jq recipes for searching the log.
It is intended for questions about DoorDash spending, ordering patterns, or what the agent did in earlier sessions. A user would reach for it when they want to review past activity or write their own queries against the log.
Running it depends on the audit hook being in place, since the skill reads the log that the hook writes. Queries are run against that log file with jq.
Limitations and requirements
Depends on the doordash-audit-log hook, which must be set up so that dd-cli invocations are recorded in the audit log; the report and queries work only from that log.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 7
doordash-order-ledger
Accountability layer for agent-driven DoorDash ordering. Works with the doordash-audit-log hook (which appends every dd-cli invocation to an append-only audit log) and the /doordash-report command to answer "what has my AI been ordering and what did it cost" from data instead of memory. Use when the user asks about their DoorDash spending, ordering patterns, what the agent did in past sessions, or wants jq recipes for querying the audit log. Covers log schema, query patterns, rotation, and privacy guidance.
As shown on www.aitmpl.com when we last read it