priority-triage

name	priority-triage
description	Cut through overwhelm to ONE thing to do next. Trigger on "I'm overwhelmed", "what should I focus on", "what should I focus on next", "too many things", "I don't know where to start", "help me prioritize", "what matters most", "I'm stuck", "I can't decide what to work on", "everything feels urgent", or any signal the founder needs help cutting through noise. Also fires on user-vocabulary equivalents: "my goals", "what are my goals", "show my goals", "review my goals" - context/priorities.md holds the goals. Returns one recommendation, not a list.
why	Cuts a long open list down to one actionable task by running four filters - the founder who is overwhelmed needs a decision, not another framework to think through.
enhance	Keep brain/flags.md updated with stall patterns and cadence/weekly-commitments.md current - triage is sharpest when it can see which items have already rolled multiple weeks.
allowed-tools	["Read","Edit","Bash"]
mcp_requirements	[]

Priority Triage - Cut Through the Noise

Runs on: reasoning - reads your files and reasons; any capable agent can run this.

The founder is overwhelmed. Find the ONE thing that unblocks the most, and recommend it. One thing.

Identity preflight (soft)

Before producing output, run:

python scripts/check-identity-ready.py

If exit code is 1, print the returned line as a one-line note above the recommendation and continue. This skill works without identity set up, but the recommendation gets sharper once /founder-os:setup has filled in core/identity.md.

Step 1: Read State (Silently)

• context/priorities.md - current goals and this week's sprint
• context/decisions.md - anything blocking progress
• context/clients.md - any time-sensitive commitments
• cadence/weekly-commitments.md - what was planned
• brain/flags.md - known stalls

Brain context (default)

Before producing output, read brain/.snapshot.md. If it is missing, or its date: line is more than 3 days old, run python scripts/brain-snapshot.py --write first and read the fresh one - a stale snapshot read as current presents last week's flags and must-dos as today's, which is worse than no memory at all. If Python is unavailable, proceed without it and say so.

If the snapshot is missing, run:

python scripts/brain-snapshot.py --write

Then read it. If the snapshot script is also missing (older install), proceed using only the profile files. Do not block.

The snapshot tells you what flags are open, what the user is working on this week, and what the latest staleness state is. Apply this context to your output where it is relevant. Do not surface every snapshot field in every output - use judgment. For priority triage, open flags ARE the unfinished work that competes for the slot, the must-do list is the existing commitment that anchors today, and recent decisions tell you what is settled and should not be re-opened.

Step 2: Apply Filters

Run through these filters in order:

Filter 1: Is anything on fire? Client deadline, commitment about to break, something that will cost money or reputation if not handled today. If yes, that's the one thing. Stop here.

Filter 2: What's blocking everything else? Often one task is a bottleneck. A decision not made, a conversation not had, a document not written. If removing one item would unblock two or more other items, that's the one thing.

Filter 3: What has the highest cost of delay? Some tasks get more expensive the longer they wait. A prospect going cold, a price not set, a hire not made. Which item costs the most by waiting another week?

Filter 4: What breaks the avoidance pattern? Check brain/flags.md for stalls. Check the weekly retro for items that have rolled multiple weeks. The thing the founder keeps avoiding is often the thing that matters most. Name it directly.

Step 3: Recommend

RIGHT NOW, THE ONE THING: [task]

WHY THIS: [one sentence - which filter caught it]

WHAT "DONE" LOOKS LIKE: [specific deliverable, not a vague outcome]

TIME NEEDED: [realistic estimate]

EVERYTHING ELSE: park it. It can wait until this is done.

Step 4: Clear the Deck

If the founder agrees, help them park everything else:

• Update cadence/daily-anchors.md with today's anchor
• Move non-urgent items to Should Do or Could Do
• If they have meetings or commitments today, name the time blocks available for deep work

Rules

• ONE recommendation. Not three options. Pick the one that matters.
• Be direct about avoidance. If the founder is dodging the hard thing, say so.
• "Everything is urgent" means nothing is prioritized. Help them see that.
• Don't add new tasks. The point is to subtract, not add.
• If they push back on your recommendation, ask: "What would you recommend if you were advising someone else in your exact situation?"