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.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 3.3w
- Forks
- 3.9k
01 前言 Front Matter
- name
- doordash-order-ledger
- metadata
- { "tags": [ "DoorDash", "Audit Log", "Spend Tracking", "Analytics", "Accountability", "CLI" ] }
- description
- 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.
- allowed-tools
- Bash(dd-cli:*), Bash(jq:*), Bash(cat:*), Bash(wc:*), Bash(tail:*), Bash(mv:*), Bash(gzip:*), Read
03 SKILL.md 正文
DoorDash Order Ledger
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.
04 同仓库更多 Skills
wealthville-pool-scoring
Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.
technical-debt-auditor
Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.
readonly-sql-guard
Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.