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.
npx skills add lonexreb/morningstar --skill rungit clone --depth 1 https://github.com/lonexreb/morningstarWrote 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.
[](https://agentmods.dev/skills/lonexreb/morningstar/run)<a href="https://agentmods.dev/skills/lonexreb/morningstar/run"><img src="https://agentmods.dev/badge/skills/lonexreb/morningstar/run/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lonexreb/morningstar/run"><img src="https://agentmods.dev/badge/skills/lonexreb/morningstar/run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.00625 |
| Opus 5 | $0.00057 | $0.00313 |
| Sonnet 5 | $0.00023 | $0.00125 |
| Haiku 4.5 | $0.00012 | $0.00063 |
Grade B, and why
run scanned grade B with 2 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 9d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- On start: `curl -X POST -H 'Content-type: application/json' --data '{"text":"[1/N] Starting: <title>"}' $WEBHOOK` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- On start: `curl -X POST -H 'Content-type: application/json' --data '{"text":"[1/N] Starting: <title>"}' $WEBHOOK` What it actually says
Run MorningStar
Execute the MorningStar autonomous coding agent. It reads a PRD from Notion, analyzes the current codebase, generates implementation tasks, and builds each one with tests and git commits.
Arguments
User provided: $ARGUMENTS
Parse the following from arguments:
- notion-url (required): Notion page URL or ID containing the PRD
- --model (optional, default: sonnet): Claude model to use
- --budget (optional, default: 50): Total USD budget
- --slack-webhook (optional): Incoming webhook URL for progress updates. Falls back to
$MORNINGSTAR_SLACK_WEBHOOK.
Instructions
- Fetch the PRD from the provided Notion URL using the Notion MCP tools.
- Analyze the codebase in the current working directory:
- Read CLAUDE.md and README.md for conventions
- Explore project structure, key source files, and existing patterns
- Generate a task list by diffing PRD requirements against what's already built
- Each task: 1-3 files, concrete implementation, acceptance criteria
- Order by dependency
- Show the task plan and ask the user to confirm before executing.
- At task boundaries post to Slack if a webhook is configured:
- On start:
curl -X POST -H 'Content-type: application/json' --data '{"text":"[1/N] Starting: <title>"}' $WEBHOOK - On completion: similar
CompletedorFailedmessage with cost.
- On start:
- Execute each task:
- Implement code changes following existing patterns
- Write/update tests
- Run tests and fix failures
- Git commit:
feat: <task title> - Report progress
- Summarize: tasks completed, tasks failed, any questions for the user. Post final summary to Slack.
Example
/morningstar:run https://notion.so/My-PRD-abc123 --model opus --budget 100 --slack-webhook https://hooks.slack.com/services/T.../B.../xyz
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.
- 9d ago First seen · 46 lines · 115 tokens per session scan B e34bc3bb5048
run is a skill published in the GitHub repository lonexreb/morningstar (1 stars, last pushed 4mo ago), licensed MIT. It adds 115 tokens to every session and 625 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
planner
Interactive planning and execution for complex tasks. Use when breaking down multi-step projects (planning) or executing approved plans through delegation (execution). Planning creates milestones with specifications; execution delegates to specialized agents. Use when you say "plan this feature", "create…
execution-plans
Manage execution plans as versioned artifacts with progress tracking and decision logs. Use when you say "create execution plan", "update plan progress", "log decision", "complete plan", or "abandon plan". Do NOT use to break work into milestones or delegate tasks (use planner).
work-operating-model
Run a 5-layer interview to elicit how a team actually works (rhythms, decisions, dependencies, institutional knowledge, friction) and emit a structured operating model. Use when you say "elicit operating model", "interview team operating model", "how does this team actually work", or "validate operating model". Do NOT…
retro
Fill an unfilled auto-retrospective skeleton for a date, or list the skeletons still pending. Use when you say retro fill, fill retro skeleton, or list pending retros. Do NOT use to run the retrospective analysis itself (this hands off to the retrospective skill), and do NOT use to write a session log.
ai-agents-docs-of-record
Runbook for this repo's documents of record. Session logs, ADRs, retrospectives, Serena memories, per-issue handoffs, plus the templates, validators, naming rules, and house prose style that bind them. Use when you say write the session log, create an ADR, fill the retro, save this to memory, which document of record.…
swarm-manager-backlog-tools
Canonical reference for the swarm-manager backlog item data model and interaction patterns. All skills that read or write backlog item artifacts should defer to this document for folder structure, artifact schemas, reading order, CLI commands, and mutation rules.