taskplane-worker-cursor

A task-execution rule set for Cursor, an AI coding editor, that uses task instructions and status files to guide implementation and verification.

In plain words
What is it for?
Use it when implementing a staged task from PROMPT.md and STATUS.md, including reading the task contract and running its specified tests.
Why use it?
It keeps work within the declared file boundaries and requires honest progress tracking and checks before completion.

Cursor rule for Cursor

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 rules/beettlle/pi-spine/taskplane-worker-cursor
Clone the repo
git clone --depth 1 https://github.com/beettlle/pi-spine

Made for: Cursor.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,449 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 $0.00048 $0.01449
Opus 5 $0.00024 $0.00724
Sonnet 5 $0.00010 $0.00290
Haiku 4.5 $0.00005 $0.00145

Measured 2d ago against content hash 4433a0bc9b68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

taskplane-worker-cursor 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 2d 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.

.cursor/rules/taskplane-worker-cursor.mdc · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Taskplane worker (Cursor)

Execute work defined in a task packet (PROMPT.md + STATUS.md). The PROMPT is the contract; STATUS is your memory between turns. Stay within scope; verify before claiming done.

Related: @taskplane-task-authoring.mdc for creating packets. Universal verification rules: general-llm-anti-patterns.mdc sections 3.8 and 3.9.

Manual activation: @taskplane-worker-cursor in chat when the agent does not auto-select this rule.

When this rule applies

Apply when the user:

  • References a task ID (PREFIX-###) or @PROMPT.md
  • Asks to execute, implement, or continue a staged task
  • Works from a task folder with active PROMPT/STATUS

Do not apply when the user only wants new packets authored—use @taskplane-task-authoring.mdc.

If the user authored packets for an external runner and did not ask you to implement in Cursor, do not start coding unless they explicitly request it.

Startup (every session)

  1. Read full PROMPT.md — Mission, Dependencies, Context to Read First, File Scope, Do NOT, Testing step, Completion Criteria, Review Level.
  2. Read STATUS.md — Current step, first unchecked checkbox in scope.
  3. Load only docs listed in Context to Read First (plus files needed for the current checkbox).
  4. Confirm dependencies are satisfied (prior tasks merged, external prerequisites met). If blocked, say so and stop.

Do not load the entire codebase when PROMPT lists specific paths.

Execution loop

  1. One checkbox at a time within the current step (or current segment in multi-repo steps).
  2. Implement only within File Scope.
  3. Update STATUS — Mark - [x] when the outcome is truly done; update step status if your workflow uses it.
  4. Tests — At step boundaries, run targeted tests when PROMPT implies them. On the dedicated Testing step, run the exact command(s) written in PROMPT.
  5. Commits — Use the task ID prefix from PROMPT's Git Commit Convention at step boundaries when committing (not necessarily after every checkbox).
  6. Verification claims — Show test/build output or state verification pending. Never claim tests pass or builds succeed without evidence.

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 48 tokens per session scan A 4433a0bc9b68

Subscribe to this mod's changes

taskplane-worker-cursor is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,449 once invoked, about $0.0002 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.