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.
git clone --depth 1 https://github.com/btspoony/mstar-harnessWrote 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/rules/btspoony/mstar-harness/repo-maintenance)<a href="https://agentmods.dev/rules/btspoony/mstar-harness/repo-maintenance"><img src="https://agentmods.dev/badge/rules/btspoony/mstar-harness/repo-maintenance/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/rules/btspoony/mstar-harness/repo-maintenance"><img src="https://agentmods.dev/badge/rules/btspoony/mstar-harness/repo-maintenance.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 | $0.00315 | $0.00315 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
repo-maintenance 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 10d 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.
What it actually says
Morning Star Repository Maintenance Rule (Cursor)
This rule applies when maintaining the Morning Star harness repository in Cursor.
Source of Truth
AGENTS.mdis the canonical maintenance policy.- Runtime behavior remains in
mstar-*skills. - Avoid duplicating long maintenance prose across runtime skill files.
What This Rule Adds (Cursor-specific)
- Keep Cursor host guidance aligned with OpenCode host guidance.
- Use
.cursor/skills/mstar-routing-eval/only for routing/prompt/rule regression work, not normal feature implementation. - If routing/gate semantics changed, include routing-eval updates and evidence.
Required Maintenance Behavior
- Read before edit, and keep edits surgical.
- Keep skill descriptions trigger-accurate.
- Use skill-creator guidance for new skills or major rewrites.
- Sync bilingual docs when onboarding or install behavior changes.
- Any change to installation/usage wording in
README.mdMUST be mirrored inREADME_CN.mdin the same change set (and vice versa). - Never modify secrets or user-owned credential files.
Quick Validation
- Before publishing the Cursor plugin:
.cursor/LOCAL-VALIDATION.md. - Lint/typecheck as relevant to edited files.
- Confirm docs and install snippets remain runnable.
- If either README changed, verify both
README.mdandREADME_CN.mdwere reviewed and updated for parity. - Summarize host-specific divergence explicitly if introduced.
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.
- 10d ago First seen · 38 lines · 315 tokens per session scan A cd462cadf691
repo-maintenance is a cursor rule published in the GitHub repository btspoony/mstar-harness (58 stars, last pushed yesterday), licensed MIT. It adds 315 tokens to every session, about $0.0016 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 2026-08-30.
Other cursor rules, from other repositories
planr-pipeline-ship
Planr Pipeline — DEV Phase orchestration (ship {feature}). Frontend ‖ backend → qa → devops ‖ doc-gen → snapshot → marker.
planr-pipeline-plan
Planr Pipeline — PO Phase orchestration (plan {feature}). Decomposes a spec into User Stories + Tasks. STOPS at the human-review gate.
planr-pipeline
Planr Pipeline orchestration — PO/DEV phase rules, R1 human gate, mode detection, runtime parity for planr-pipeline.
implement-task-list
Implement Task List — context-aware task implementation guide for planr-pipeline.
openplanr-operate
Agent-native OpenPlanr Operating Board workflow for Cursor.
agile-checklist
Agile Development Checklist — guides you through the 5-phase agile workflow for planr-pipeline.