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 agentmods add rules/beettlle/pi-spine/spine-worker-cursorgit clone --depth 1 https://github.com/beettlle/pi-spineWrote 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/beettlle/pi-spine/spine-worker-cursor)<a href="https://agentmods.dev/rules/beettlle/pi-spine/spine-worker-cursor"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/spine-worker-cursor.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.01013 |
| Opus 5 | $0.00029 | $0.00507 |
| Sonnet 5 | $0.00012 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
spine-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-spine worker (Cursor, manual)
Manually execute a spine task packet in Cursor when no spine batch is active on the same tasks. Inherits the Taskplane worker loop; adds spine Contract and Testing-step requirements.
Related: @taskplane-worker-cursor.mdc (execution loop—follow it); @spine-task-authoring.mdc (authoring); @spine-operator-cursor.mdc (batch ops). Verification: general-llm-anti-patterns.mdc §3.8–3.9.
Manual activation: @spine-worker-cursor.
When this rule applies
Apply when the user:
@PROMPT.mdunder the spine tasks root and asks to implement- References
SP-###for in-Cursor work
Do not apply when:
- User wants new packets →
@spine-task-authoring.mdc - User wants batch/gate/integrate →
@spine-operator-cursor.mdc spine statusshows an active batch on the same task scope → stop; use operator rule or wait
Startup (every session)
- Read
.spine/spine-config.json—paths.tasksRoot,testing.*,contract.*. - Read full
PROMPT.md— Mission, Dependencies, File Scope, ## Contract, Do NOT, Testing step, Completion Criteria. - Read
STATUS.md— current step, first unchecked checkbox. - Load only docs in Context to Read First.
- Confirm dependencies satisfied (
dependencies.json+ prior tasks merged).
If a spine batch is running on overlapping tasks, report conflict and defer to @spine-operator-cursor.mdc.
Execution loop
Follow @taskplane-worker-cursor.mdc:
- One checkbox at a time within current step.
- Implement only within File Scope.
- Update STATUS honestly at step boundaries.
- Run tests per PROMPT; on Testing step run exact command(s).
- Commits:
feat(SP-###): …per Git Commit Convention. - Show test/build output or state verification pending.
Spine additions (beyond Taskplane worker)
Contract table
Satisfy every field in ## Contract before claiming done:
| Field | Worker action |
|---|---|
testCommand |
Run on Testing step; show output |
fileScopeMustChange |
Ensure each path has intended changes |
fileScopeMustNotChange |
Do not edit; if required, escalate |
completionCriteria |
Map to Completion Criteria checkboxes |
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.
- 5d ago First seen · 95 lines · 58 tokens per session scan A 96c39f74783a
spine-worker-cursor is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,013 once invoked, about $0.0003 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.