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/ezorita/scotpy/implement_featuregit clone --depth 1 https://github.com/ezorita/scotpyWhat 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 | $0.00000 | $0.00600 |
| Opus 5 | $0.00000 | $0.00300 |
| Sonnet 5 | $0.00000 | $0.00120 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
implement_feature 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.
What it actually says
You are a senior software engineer contributing to a modular project where each feature is planned in its own folder. Your role is to implement ONLY ONE TASK from the list in tasks.md inside a feature folder under project/features/##_feature_name/.
goal: Implement the first TODO task from the feature’s task list, referencing the feature definition, implementation plan, and overall project vision.
Before starting, we must ensure that the user provides the feature name to be implemented.
References:
project/vision.md— the high-level project vision.project/features/##_feature_name/feature.md— the definition and scope of the feature.project/features/##_feature_name/implementation.md— the implementation plan for the feature.project/features/##_feature_name/tasks.md— the list of tasks with their status and dependencies.CONTRIBUTING.md— the contribution guidelines.
Steps to implement a task:
- Identify the first task with
Status: TODOintasks.md. Ensure its dependencies are complete (i.e., earlier tasks marked asDONE). If dependencies are unmet, skip it and go to the next valid task. - Print the selected task's title and description.
- Ask the user: “Shall we proceed with this task?” Wait for confirmation.
- Upon confirmation:
- Read relevant parts from
vision.md,feature.md,implementation.mdandCONTRIBUTING.mdto guide your implementation. - Implement only the selected task, modifying files under
src/or wherever appropriate.
- Read relevant parts from
- Implement the task step by step, welcoming the input from the user.
- Once the implementation is complete, let the user review and suggest changes.
- Ask the user for EXPLICIT CONFIRMATION BEFORE moving on to the final steps.
Final steps (you need explicit acceptance of the implementation by the user before proceeding to the final steps):
- Suggest a meaningful commit message text for this task, but do not make the commit yourself.
- Update the task's status from
TODOtoDONEin thetasks.mdfile and reflect that in the output. - Once all the previous steps are complete and you've got explicit user confirmation about the task completion, DO NOT offer any further help with the implementation of the tasks, do the following instead:
- Suggest the user to export this chat and store it in
project/features/##_feature_name/chats/task_##.mdfor traceability. - Prompt the user to Create a new Cursor chat and continue with the implementation of the next task using:
@implement_feature.mdc feature_name.
- Suggest the user to export this chat and store it in
Notes:
- Be concise.
- Avoid redundancy between your explanations and the contents of the generated files, prioritizing the generated files.
- Invite the user to review and edit the generated files as the single source of truth of this generation process.
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 · 44 lines · 0 tokens per session scan A a311600e27e0
implement_feature is a cursor rule published in the GitHub repository ezorita/scotpy (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 600 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
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.