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/pueraeternis/agentic-project-template/03-plan-implementationgit clone --depth 1 https://github.com/pueraeternis/agentic-project-templateWhat 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 | $0.00581 | $0.00581 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
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.
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:
- Read the active implementation plan.
- Confirm the implementation scope.
- Review the acceptance criteria.
- Review the project architecture.
- 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:
AGENTS.mdPROJECT.mdROADMAP.mdARCHITECTURE.mdENGINEERING.md- Relevant ADRs
- 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:
- Update
ARCHITECTURE.md. - Create or update an ADR when appropriate.
- Continue implementation only after the architecture has been updated.
If engineering conventions change:
- Update
ENGINEERING.md. - Update related operational documentation if required.
Implementation Principles
Prefer:
- simple solutions;
- explicit logic;
- maintainable code;
- deterministic behavior;
- documented conventions.
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.
- 2d ago First seen · 157 lines · 581 tokens per session scan A 870b2d38fd98
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.
Other cursor rules, from other repositories
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
implementation-workflow
Required plan-first workflow for any implementation request (steps 1–5).
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
nauro-context
Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.