What is planr-pipeline-plan?

A planning workflow that breaks a feature specification into user stories and implementation tasks. It stops after producing those planning files so a person can review them.

Use it with commands such as “plan feature” to find the specification, create user stories and tasks, and prepare work for the later development phase.

It turns a broad feature request into smaller pieces of work without starting implementation before approval.

planr-pipeline-plan — Cursor rule for Cursor by openplanr

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/openplanr/planr-pipeline

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/openplanr/planr-pipeline/planr-pipeline-plan/github.svg)](https://agentmods.dev/rules/openplanr/planr-pipeline/planr-pipeline-plan)

Your own site

<a href="https://agentmods.dev/rules/openplanr/planr-pipeline/planr-pipeline-plan"><img src="https://agentmods.dev/badge/rules/openplanr/planr-pipeline/planr-pipeline-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/openplanr/planr-pipeline/planr-pipeline-plan"><img src="https://agentmods.dev/badge/rules/openplanr/planr-pipeline/planr-pipeline-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,076 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.02076
Opus 5	$0.00016	$0.01038
Sonnet 5	$0.00006	$0.00415
Haiku 4.5	$0.00003	$0.00208

Measured 12d ago against content hash da72f0e60b06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

planr-pipeline-plan 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 12d 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/planr-pipeline-plan.mdc · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan {feature} — PO Phase orchestration (Cursor)

When the user says "plan {feature}" (or "decompose {feature}", or similar), follow this rule end-to-end. The argument {feature} is the feature slug (no feat- or spec- prefix).

Hard rule R1: this command STOPS after writing US/Task files. The user must review and explicitly say "ship {feature}" before any DEV-Phase work.

--dry-run: same contract as Claude plugin commands/plan.md / commands/procedures/plan-step0-preflight.md § 0.5b (strategy + hypothetical agent list — NO writes / dispatch).

Step 1 — Mode detection + input validation

1a — Detect planr spec mode

Before any other checks, look for .planr/config.json at the project root:

If .planr/config.json exists AND its idPrefix.spec field is set, assume spec-driven mode.
In spec-driven mode, scan .planr/specs/ for a directory matching ^[A-Z]+-\d{3}-{feature}$. The first match resolves to SPEC_DIR = .planr/specs/<that-dir> (e.g., .planr/specs/SPEC-001-auth-flow/ for feature=auth-flow).
Otherwise, fall through to default mode (output/feats/feat-{feature}/).

For the rest of this rule, internally maintain MODE = "spec-driven" or "default".

1b — Validate required inputs

Required (default mode):

input/specs/spec-{feature}.md — fail with: "spec-{feature}.md not found. Create it (or use spec-driven mode by adding idPrefix.spec to .planr/config.json and re-running)."
input/tech/stack.md — fail with: "input/tech/stack.md not found. Create it from .cursor/rules/templates/stack.md.tpl."

Required (spec-driven mode):

<SPEC_DIR>/SPEC-NNN-{feature}.md — if missing, auto-scaffold (see below).
input/tech/stack.md — see Self-healing below.

Auto-scaffolding the spec shell

When <SPEC_DIR>/SPEC-NNN-{feature}.md is missing, scaffold instead of aborting:

Ensure .planr/config.json exists. If absent, write:

{
  "projectName": "<derive from package.json name or repo dir>",
  "outputPaths": { "agile": ".planr" },
  "idPrefix": { "spec": "SPEC" }
}

Ensure .planr/specs/ exists.
Determine the next SPEC ID. Scan .planr/specs/ for SPEC-NNN-*/ dirs, take the highest NNN, increment. Three-digit format (SPEC-001).
Create .planr/specs/SPEC-NNN-{feature}/{stories,tasks,design}/.
Read .cursor/rules/templates/spec-driven.md.tpl (if present; otherwise inline a minimal v1.0.0 spec template). Substitute , , , . Write to <SPEC_DIR>/SPEC-NNN-{feature}.md.

Print and abort:

✓ Scaffolded SPEC-NNN-{feature} at .planr/specs/SPEC-NNN-{feature}/
  Edit the spec body, then re-run: plan {feature}

Do not invoke any role. Decomposition runs only on the second invocation, after the user has filled in the body.

Read the full file on GitHub · 197 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.

12d ago First seen · 197 lines · 32 tokens per session scan A da72f0e60b06

Subscribe to this mod's changes

planr-pipeline-plan is a cursor rule published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,076 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.

Claude Code Code Generation Planning Project management ai-agents claude-code-plugin spec-driven subagents

planr-pipeline-plan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/plan {feature} — PO Phase orchestration (Cursor)

Step 1 — Mode detection + input validation

1a — Detect planr spec mode

1b — Validate required inputs

Auto-scaffolding the spec shell

What this file has done since we first saw it

Other cursor rules, from other repositories

sddp

archcore-context

neuraforge

flutter-forge

ponytail

angular-20