morning-loop

morning-loop is a command for Claude Code from ARCASSystems/FounderOS. It costs 58 tokens per session (363 once invoked), scanned A, original, MIT.

A once-a-day morning question loop that asks up to four focused questions, saves the answers in their relevant files, and names one step for today.

In plain words
What is it for?
Use it each morning to answer only the questions raised by your current notes, close the items those answers resolve, and record a coaching line for the day.
Why use it?
It helps resolve waiting decisions and unfinished items without creating unnecessary questions or starting other work automatically.

Command for Claude Code

Part of the founder-os plugin — 9 skills, 45 commands, 6 hooks shipped together

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/morning-loop
Clone the repo
git clone --depth 1 https://github.com/ARCASSystems/FounderOS

Made for: Claude Code.

Or install founder-os, the plugin that ships this one along with the rest of its 9 skills, 45 commands, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for morning-loop

README.md
[![agentmods](https://agentmods.dev/badge/commands/arcassystems/founderos/morning-loop.svg)](https://agentmods.dev/commands/arcassystems/founderos/morning-loop)
Your own site
<a href="https://agentmods.dev/commands/arcassystems/founderos/morning-loop"><img src="https://agentmods.dev/badge/commands/arcassystems/founderos/morning-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 363 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 $0.00058 $0.00363
Opus 5 $0.00029 $0.00181
Sonnet 5 $0.00012 $0.00073
Haiku 4.5 $0.00006 $0.00036

Measured 3d ago against content hash 704507dff1a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

morning-loop 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 3d 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/morning-loop.md · 26 lines

What it actually says

Founder OS morning loop

Run the morning-loop skill at skills/morning-loop/SKILL.md end to end.

Procedure

  1. Check brain/log.md for a #morning-loop entry dated today. If one exists, say so and stop unless the founder explicitly asks to run it again.
  2. Read skills/morning-loop/SKILL.md.
  3. Gather silently (step 1), pick at most four questions (step 2), ask them in one batch with a recommendation first on each.
  4. Write every answer back through the owning file, then close the thing that raised it.
  5. Score yesterday's coach line and name today's one step. Write the Coach: line into the closing log entry.
  6. Report in under 15 lines, ending with the coach line in plain words.

Rules

  • Four questions maximum. If nothing qualifies, say "Nothing needs you this morning" and stop. Never invent a question to fill the batch.
  • Every answer lands in a file, and the source that asked gets closed in the same pass.
  • Parse a freeform answer ("1 yes, 2 skip") rather than asking for a tidier format.
  • Never send anything, never run a recurring job, never start a build.
  • No em dashes or en dashes. No banned words.
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. 3d ago First seen · 26 lines · 58 tokens per session scan A 704507dff1a0

Subscribe to this mod's changes

morning-loop is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 20d ago), licensed MIT. It adds 58 tokens to every session and 363 once invoked, about $0.0003 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.