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-task-authoringgit 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-task-authoring)<a href="https://agentmods.dev/rules/beettlle/pi-spine/spine-task-authoring"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/spine-task-authoring.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 | $0.00000 | $0.02696 |
| Opus 5 | $0.00000 | $0.01348 |
| Sonnet 5 | $0.00000 | $0.00539 |
| Haiku 4.5 | $0.00000 | $0.00270 |
Grade A, and why
spine-task-authoring 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 yesterday.
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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-spine task authoring
Author spine-compatible task packets for autonomous execution via pi-spine (spine batch start, /spine). Packets are file contracts; pi-spine workers run in lane worktrees with journal, review, and integrate gates—the PROMPT defines what to build, not how the orchestrator runs.
Related: @spine-operator-cursor.mdc for batch operations; @spine-worker-cursor.mdc for manual in-Cursor implementation; @taskplane-task-authoring.mdc when no .spine/spine-config.json exists. Templates: @.cursor/rules/taskplane/prompt-template.md, @.cursor/rules/taskplane/status-template.md. Deep decomposition: pi-spine create-spine-tasks skill (pi install npm:pi-spine)—link only, do not vendor.
When this rule applies
Apply when the user asks to:
- Create, stage, or decompose spine tasks (
SP-*,spine-tasks/, spine batch) - Write or update spine
PROMPT.md,STATUS.md,dependencies.json, or tasks-rootCONTEXT.md - Migrate or extend Taskplane packets for pi-spine
Do not apply for:
- Batch control (
spine batch start, gate, integrate) →@spine-operator-cursor.mdc - Implementing product code →
@spine-worker-cursor.mdc - Generic Taskplane packets with no spine config →
@taskplane-task-authoring.mdc
If intent is ambiguous (author vs operate vs implement), ask once.
Orchestration artifacts vs repo docs
Spine task files under the configured tasks root are orchestration artifacts, not unsolicited documentation. Creating them when the user requests spine task work is allowed. See documentation-policy.mdc (pi-spine task packets exception).
Do not hand-edit .spine/runtime/**, .spine/batch-state.json, or create .DONE / .reviews/ at author time.
Prerequisites
.spine/spine-config.jsonexists (spine init). If missing, tell the user to runspine initbefore authoring.- Read config keys:
paths.tasksRoot,testing.build/testing.test/testing.testWithCoverage,referenceDocs,standards,neverLoad,contract.mode,contract.legacyTaskIdPrefixes.
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.
- yesterday Changed · +13 lines 196826969f33
- 6d ago First seen · 195 lines · 0 tokens per session scan A 43e5acf6b0d3
spine-task-authoring is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,696 tokens. 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
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
elite-orchestrator
Elite orchestrator for mission-critical, enterprise-scale tasks requiring strategic coordination of 7+ agents across all domains. Makes architectural decisions, manages risk, ensures business continuity, and delivers enterprise-grade outcomes. Use for platform migrations, security incidents, multi-system integrations…
feedback-enhanced
Enhanced feedback mechanism with 1-hour timeout - 增强反馈机制，1小时超时.
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
linear-in-review
After finishing a Linear issue, set its status to In Review (never Done).