Checklists
Read a project's checklists — onboarding and the daily Beast Mode operations bar — with derived item states and per-day history.
A checklist is the contract between Moab and you about what "working" means.
Every project carries two: the onboarding list ("Get your CRM working") and
Beast Mode, the daily operations bar. Item states are derived on every
read from real data — a green check means a bounded D1 query said so, never
that an agent claimed it. Beast Mode is evaluated once a day by a scheduled
beast-mode-checklist run that publishes the day's verdicts, evidence, and a
one-line summary; the same rows feed the card on the home page, this API, and
the bottom of the weekly report.
Read a project's checklists
curl -H "Authorization: Bearer $DASH_PAT" \
"https://moabcrm.com/api/v1/projects/<project_id>/checklists?include_history=7"The response returns every list with derived item states. include_history=7
adds Beast Mode day rows, each {day, summary, verdicts[], cost_usd} — one row
per UTC day, newest first, where each verdict is
{item_id, verdict: "pass"|"fail"|"skip", detail}.
Freshness — green, yellow, red
Beast Mode's freshness is derived at read time and never stored: the latest
published day equal to today (UTC) is green, yesterday is yellow, anything
older — or no run at all — is red. No run today means red; success is never
inferred from silence.
Update from an agent (MCP)
checklist_list— the evaluated state (passinclude_history: 7for the day rows).checklist_item_update— an agent may writein_progressorblocked(with a named gap) plusdetail/href/evidence.doneis refused (checklist_done_is_derived): done comes from the item's own data query or predicate, never from a tool call.checklist_run_publish— Beast Mode's ONE terminal write: the day's verdicts and summary. Every declared judgment item must be verdicted or the whole publish fails (checklist_verdict_missing); publishing again the same UTC day replaces that day's record.
How Beast Mode derives done
Fact items (e.g. "≥5 distinct subject lines today") derive from windowed data
queries the platform runs itself — window: today filtered against the
envelope created_at (creation, never last write — sync churn does not count
as "today"). Judgment items (e.g. "subjects span the
simple→complex spectrum") use daily_verdict:<item_id>: they are done iff
TODAY's published record carries verdict: "pass" for that item. The
publishing skill writes evidence; the platform derives the state.
Let the agent do it
The beast-mode-checklist skill runs once a day per project on its own
schedule (visible under Settings → Usage → Scheduled Tasks, with run-now,
pause, and resume). It reads the day's drafts, agents, content, and channel
state, computes each verdict, and ends in exactly one checklist_run_publish.