03-plan-implementation

A set of repository-wide rules for implementing software changes from an approved plan. It requires reviewing project documentation, architecture, engineering decisions, and acceptance criteria before coding.

In plain words
What is it for?
Carrying out planned code changes in a repository while checking its architecture, requirements, project documents, and technical decisions first.
Why use it?
It keeps implementation within the agreed scope and prevents unrelated refactoring or invented features. It also provides a process for handling conflicts between documentation and code.

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/pueraeternis/agentic-project-template/03-plan-implementation
Clone the repo
git clone --depth 1 https://github.com/pueraeternis/agentic-project-template

Made for: Cursor.

Per session 581 This file is loaded in full into every session.
When invoked 581 The same file — it is already loaded in full.
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 $0.00581 $0.00581
Opus 5 $0.00291 $0.00291
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 2d ago against content hash 870b2d38fd98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

03-plan-implementation 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/03-plan-implementation.mdc · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.


Plan-Driven Implementation

Implement only work authorized by an approved implementation plan.

Before writing code:

  1. Read the active implementation plan.
  2. Confirm the implementation scope.
  3. Review the acceptance criteria.
  4. Review the project architecture.
  5. Review the project engineering decisions.

Implementation is the execution of an approved engineering contract.

Do not invent new work.


Required Project Context

Before implementation, review:

  1. AGENTS.md
  2. PROJECT.md
  3. ROADMAP.md
  4. ARCHITECTURE.md
  5. ENGINEERING.md
  6. Relevant ADRs
  7. Active implementation plan

If documentation conflicts with implementation, resolve the documentation first rather than silently changing the code.


Scope Control

Implement only the approved scope.

Do not introduce:

  • unrelated refactoring;
  • speculative engineering;
  • premature optimization;
  • future roadmap phases;
  • undocumented functionality.

One implementation should correspond to one approved implementation plan.

If additional work is discovered:

  • stop;
  • document the finding;
  • recommend creating or updating a plan.

Never silently expand scope.


Architectural and Engineering Boundaries

Respect both:

  • architectural decisions (ARCHITECTURE.md);
  • engineering decisions (ENGINEERING.md).

Do not:

  • violate architectural boundaries;
  • bypass dependency rules;
  • duplicate responsibilities;
  • ignore documented engineering conventions.

If architectural changes are required:

  1. Update ARCHITECTURE.md.
  2. Create or update an ADR when appropriate.
  3. Continue implementation only after the architecture has been updated.

If engineering conventions change:

  1. Update ENGINEERING.md.
  2. Update related operational documentation if required.

Implementation Principles

Prefer:

  • simple solutions;
  • explicit logic;
  • maintainable code;
  • deterministic behavior;
  • documented conventions.

Read the full file on GitHub · 157 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 · 157 lines · 581 tokens per session scan A 870b2d38fd98

Subscribe to this mod's changes

03-plan-implementation is a cursor rule published in the GitHub repository pueraeternis/agentic-project-template (2 stars, last pushed 2mo ago), licensed MIT. It adds 581 tokens to every session, about $0.0029 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.