morning-status-brief
Produce a read-only morning project status from the LLM-OS Project Control Tower and Agent Run Queue.
Skill by armin-haghi
Chalk Labs
Need help deploying morning-status-brief?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/armin-haghi-morning-status-brief
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/morning-status-brief
What's inside
- Skill name
morning-status-brief- Description
- Produce a read-only morning project status from the LLM-OS Project Control Tower and Agent Run Queue.
- License
- MIT
- Instructions
- 287 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Morning Status Brief Use this skill when the human asks for: - "morning project status" - "morning status" - "project status" - "queue status" - "what needs my decision today" - "what should I work on today" This skill produces a daily operating brief from the canonical `llm-os` portfolio and run surfaces: - Project Control Tower - Agent Run Queue Default behavior is read-only. Do not update Notion, repo docs, or run records unless the human explicitly asks. ## Private surface rule Do not commit or rely on private Notion IDs, page URLs, database IDs, data-source IDs, or connector-specific IDs in this skill. Resolve private surfaces by: 1. connected workspace/tool search using the canonical names `Project Control Tower` and `Agent Run Queue` 2. a link supplied by the human in the current session 3. ignored local config such as `.llm-os.local.yaml` for private local workflows 4. asking the human for access or pasted content if needed ## Data access order Prefer direct data-source/database query when the current connector supports it. If direct query is unavailable, fall back to: 1. search the Project Control Tower and Agent Run Queue by canonical name or data-source scope 2. fetch individual result pages 3. extract fields from page properties Do not ask the human to summarize project status if the Notion surfaces are accessible. If a tool cannot access one surface, report partial results and name the missing surface. ## Timestamp rule Use `YYYY-MM-DD HH:mm` in the human/operator's local timezone for operational state timestamps. Do not include seconds. ## Read from Project Control Tower Read these fields when available: - Project - Status - Stage - Active Milestone - Freshness - Last Reviewed - Owner - Blocker - Next Decision - Next Action - Canonical Repo - Execution Surface - Commercial Signal - Notion Page - Repo Branch - Repo Latest Commit - Repo State Checked - Repo Review Needed - Repo Review Reason - Repo Review Agent - Notion Writeback Status - Notion Writeback Reason - Notion Last Synced - Followup Run Needed - Followup Run Reason - Followup Agent Classify projects: - `active`: status is `active-build` - `ready`: status is `build-ready` - `shaping`: status is `shaping` - `parked`: status is `parked` - `archived`: status is `archived` - `stale`: freshness is `stale` or `unknown` ## Read from Agent Run Queue Read these fields when available: - Run - Project - Status - Priority - Agent Contract - Goal - Human Decision Needed - Result Handoff - Input Source - Required Read Path - Write Back Targets - Last Touched Classify runs: - `waiting_human`: status is `waiting-human` - `blocked`: status is `blocked` - `in_flight`: status is `in-flight` - `ready`: status is `ready` - `historical`: status is `done` or `stale`
From armin-haghi/llm-os, MIT.
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 3, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/armin-haghi/llm-os
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get morning-status-brief running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
morning-status-brief skill. Agent Mart. https://agentmart.dev/skills/armin-haghi-morning-status-brief (last updated 2026-10-24)