next

A next-action recommendation command that reviews your priorities, clients, work rhythm, and notes, then suggests one thing to focus on.

In plain words
What is it for?
Use it when you are unsure what to do next and want one read-only recommendation based on your current files and role.
Why use it?
It removes the need to compare every open task yourself when deciding what deserves attention next.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/arcassystems/founderos/next
Clone the repo
git clone --depth 1 https://github.com/ARCASSystems/FounderOS

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,763 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.01763
Opus 5 $0.00020 $0.00881
Sonnet 5 $0.00008 $0.00353
Haiku 4.5 $0.00004 $0.00176

Measured 2d ago against content hash c28374ce4b43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

next scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/next.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/next

Recommend ONE next action across everything the founder is currently doing. This is the orchestration command. It reads priorities, clients, cadence, and brain, then reasons about what to recommend.

Procedure (in order)

Step 0. Route by operator type

Before ranking, check who this is for. Read the **Role:** line under ## Basics in core/identity.md, and whichever snapshot block the file carries (## Founder Snapshot or ## Role Snapshot), if any. The role is the gate, not the profile variant - the variant field never holds team_of_one.

If the role is founder or team_of_one and a ## Founder Snapshot block exists, OR the role is operator and a ## Role Snapshot block exists, do NOT run the generic ranking below. Run the founder-next-move propose engine instead. It reads the same files, works out where they actually are, and names the single highest-leverage move - toward a paying customer on the founder path, toward the work they own on the operator path - with a three-option close. The engine handles a thin snapshot itself - it proposes a capture move when fields are missing - so route to it whenever the matching block exists, even half-filled. Never send someone who has a snapshot to the generic ranking.

For every other case (no identity file, a student / career-mover install with no snapshot block, or an older install carrying neither block), continue with the ranking in Steps 1 to 5 below.

Step 1. Verify setup

Read context/priorities.md. If the file does not exist or only contains template placeholders, reply:

Priorities not set up. Run /founder-os:setup and add at least one weekly priority, or edit context/priorities.md directly. I can't recommend a next action without knowing what matters this week.

Stop.

Step 2. Read context

Read these files in this order. Use whatever is present, skip what is missing.

  1. context/priorities.md - this week's must/should/could (REQUIRED)
  2. context/clients.md - active deals and prospects (REQUIRED)
  3. brain/needs-input.md - any open ask blocking a workflow (skip if file missing)
  4. brain/flags.md - OPEN flags only (skip if file missing)
  5. context/decisions.md - any item whose re-trigger condition has fired today (skip if file missing)
  6. cadence/daily-anchors.md - today's anchors (skip if file missing or stale)
  7. cadence/weekly-commitments.md - this week's commitments (skip if file missing or stale)
  8. brain/log.md - last 3 entries only (skip if file missing)

Read the full file on GitHub · 119 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 119 lines · 40 tokens per session scan A c28374ce4b43

Subscribe to this mod's changes

next is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 18d ago), licensed MIT. It adds 40 tokens to every session and 1,763 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.