implement-task-list

An implementation guide that tells a coding agent to read the full planning hierarchy before changing code. The hierarchy links a task to its user story, feature, and larger epic.

In plain words
What is it for?
Use it when implementing a task list so the agent can inspect the selected task and its related planning documents before starting the first unfinished subtask.
Why use it?
It reduces the risk of implementing a small task without understanding its requirements, acceptance tests, dependencies, or broader purpose.

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/openplanr/planr-pipeline/implement-task-list
Clone the repo
git clone --depth 1 https://github.com/openplanr/planr-pipeline

Made for: Cursor.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,001 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 $0.00014 $0.01001
Opus 5 $0.00007 $0.00500
Sonnet 5 $0.00003 $0.00200
Haiku 4.5 $0.00001 $0.00100

Measured 2d ago against content hash 8c69e0a56224, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-task-list 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/implement-task-list.mdc · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Task List

You are an implementation assistant for planr-pipeline. Before writing any code, you MUST gather full planning context by reading the artifact hierarchy.

Context-Gathering Protocol

Before implementing ANY subtask, follow this exact sequence:

Step 1: Read the Task List

  • Open the task file from .planr/tasks/ (e.g., TASK-001-*.md)
  • Parse the frontmatter to find storyId or featureId
  • Identify the target subtask (first unchecked - [ ] item)
  • Read ALL subtasks to understand the full scope and dependencies

Step 2: Read the Parent Chain (MANDATORY)

Follow the artifact hierarchy upward — each level adds critical context:

  1. User Story.planr/stories/US-XXX-*.md

    • Read the full story (role, goal, benefit, acceptance criteria)
    • Find and read the matching Gherkin file: .planr/stories/US-XXX-gherkin.feature
    • Extract the parent featureId from frontmatter
  2. Feature.planr/features/FEAT-XXX-*.md

    • Read the full feature (overview, functional requirements, technical considerations)
    • Extract the parent epicId from frontmatter
  3. Epic.planr/epics/EPIC-XXX-*.md

    • Read the epic summary (business value, problem statement, success criteria)
    • This provides the WHY behind the work

Step 3: Read Architecture Context

  • Read ALL ADRs in .planr/adrs/ — these are binding technical decisions
  • Check .planr/checklists/AGILE-DEVELOPMENT-GUIDE.md for current progress

Step 4: Scan the Codebase

Before writing code, understand what exists:

  1. Identify the tech stack — Read package.json, tsconfig.json, or equivalent
  2. Scan the source tree — List directories under src/ (or project root)
  3. Read architecture files — Look for these high-priority files:
    • Type definitions: src/models/types.ts, src/types/index.ts, or src/types.ts
    • Core services: src/services/ — understand CRUD patterns
    • Entry point: src/index.ts, src/main.ts, or src/app.ts — understand registration patterns
    • Config: src/config.ts or src/services/config-service.ts
  4. Find related files — Search for files matching keywords from the task description
  5. Check project rules — Read .planr/rules.md if it exists (MANDATORY rules)

Read the full file on GitHub · 92 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 · 92 lines · 14 tokens per session scan A 8c69e0a56224

Subscribe to this mod's changes

implement-task-list is a cursor rule published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 28d ago), licensed MIT. It adds 14 tokens to every session and 1,001 once invoked, about $0.0001 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.