mstar-cursor-plan-mode

mstar-cursor-plan-mode is a cursor rule for Cursor from btspoony/mstar-harness. It costs 1,038 tokens per session, scanned A, original, MIT.

A Cursor Plan mode rule that keeps Morning Star’s saved plan files and status records in sync with the plan shown during a session. It also requires each task to have its own Git commit.

In plain words
What is it for?
Use it when planning and implementing tasks with Cursor Plan mode and the Morning Star harness. It helps initialize planning records, save the plan, update status, and verify task commits.
Why use it?
It prevents the visible session plan from becoming the only record of work and makes task completion traceable in the repository.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when planning and implementing tasks with Cursor Plan mode and the Morning Star harness. It helps initialize planning records, save the plan, update status, and verify task commits.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/btspoony/mstar-harness/mstar-cursor-plan-mode
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.

Clone the repo
git clone --depth 1 https://github.com/btspoony/mstar-harness

Made for: Cursor.

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 mstar-cursor-plan-mode

README.md
[![agentmods](https://agentmods.dev/badge/rules/btspoony/mstar-harness/mstar-cursor-plan-mode/github.svg)](https://agentmods.dev/rules/btspoony/mstar-harness/mstar-cursor-plan-mode)
Your own site
<a href="https://agentmods.dev/rules/btspoony/mstar-harness/mstar-cursor-plan-mode"><img src="https://agentmods.dev/badge/rules/btspoony/mstar-harness/mstar-cursor-plan-mode/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.

agentmods 80×15 button for mstar-cursor-plan-mode

Your own site · 80×15
<a href="https://agentmods.dev/rules/btspoony/mstar-harness/mstar-cursor-plan-mode"><img src="https://agentmods.dev/badge/rules/btspoony/mstar-harness/mstar-cursor-plan-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,038 This file is loaded in full into every session.
When invoked 1,038 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01038 $0.01038
Opus 5.5 $0.00415 $0.00415
Sonnet 5.5 $0.00208 $0.00208
Haiku 4.5 $0.00104 $0.00104

Measured 14d ago against content hash e81662cd2d65, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mstar-cursor-plan-mode 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 14d 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.

rules/mstar-cursor-plan-mode.mdc · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Morning Star × Cursor Plan mode

When the Morning Star harness plugin or /pm is active and Cursor Plan mode applies (CreatePlan / built-in plan todos):

SSOT vs CreatePlan

  • SSOT for plans and status: {HARNESS_DIR} (default .mstar/, legacy .agents/) — {PLAN_DIR}/<plan-id>-<name>.md, {HARNESS_DIR}/status.json, specs under {SPECS_DIR} when used.
  • CreatePlan is a session mirror only; do not treat the Cursor plan file URI as the only plan record.

CreatePlan todos (mandatory prefix)

Before any implement/code todo, CreatePlan must list these three bootstrap todos (in order) and complete them on disk:

  1. harness-init — create harness dirs + initialize status.json from template when missing
  2. spec-register — add plans[] row with plan_id and file path
  3. mirror-plan — write the SSOT main plan markdown under .mstar/plans/ (or resolved {PLAN_DIR})

Implement todo done gate

Do not mark an implement todo complete until:

  • git commit on the authorized Working branch for that task id (no end-of-plan batch commit unless PM allowed) Each todo's commit uses the configured identity; missing/failing identity is Blocked, never fabricate or use -c identity overrides → mstar-roles/references/_shared/leaf-executor-core.md § Git NEVER (repo writes).
  • matching checkbox - [x] in the SSOT plan file
  • status.json updated when the coordination round requires it
  • evidence: real git log -1 --format='%h %an <%ae>'

Drift and paths

  • Keep CreatePlan body and SSOT plan file aligned when scope changes.
  • Use SSOT paths in Plan Path / Context Loaded, not only the Cursor plan URI.

mstar-iteration Phase 1 in Plan mode

When Plan mode is used to start a new iteration:

  • CreatePlan once as a blank session carrier with pending preparation / Build-bound todos; record its path. The Phase 1 bridge overrides early formal dual-write/bootstrap until the prototype checkpoint passes.
  • Feedback loop: update the same session carrier and, when host writes permit, the iteration-package prototype. No formal compass/guides/plans/specs before approval of the presented current prototype. Do not turn feedback into a mandatory questionnaire.
  • Feedback-close permits minimal deferred clarification for blocking gaps; it is not design approval. Prototype feedback/revision/re-presentation and restricted-write recovery follow mstar-host → references/cursor-plan-mode-bridge.md (no alternate tool/child bypass).
  • Never open a second CreatePlan. Consolidate an accidental duplicate into the original and remove it only when host permissions permit.
  • Do not dispatch Review & Edit, commit, or create the integration branch until the user clicks Build.
  • Detail: mstar-host → references/cursor-plan-mode-bridge.md § mstar-iteration Phase 1 in Plan mode.

Read the full file on GitHub · 63 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. 14d ago Changed · +1 lines · +58 tokens per session e81662cd2d65
  2. 24d ago Changed · +77 tokens per session cb63ec2a1d2b
  3. 1mo ago First seen · 62 lines · 903 tokens per session scan A fadfd7bc18c8

Subscribe to this mod's changes

mstar-cursor-plan-mode is a cursor rule published in the GitHub repository btspoony/mstar-harness (64 stars, last pushed yesterday), licensed MIT. It adds 1,038 tokens to every session, about $0.0042 per session on Opus 5.5. 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.