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 skills/superplanehq/superplane/clean-codenpx skills add superplanehq/superplane --skill clean-codegit clone --depth 1 https://github.com/superplanehq/superplaneWhat 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 | $0.00093 | $0.01280 |
| Opus 5 | $0.00046 | $0.00640 |
| Sonnet 5 | $0.00019 | $0.00256 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
clean-code 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- clean-code — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code
These are mandatory engineering standards for any code you write, change, or review while this skill is active. They are language-agnostic: apply them in whatever language the project uses, respecting that language's idioms.
If there is tension between speed and cleanliness, choose the clean solution unless there is a demonstrated operational emergency. If a shortcut is unavoidable, contain it, make it obvious, and leave the code safe to clean up later.
For detailed rationale, examples, and design heuristics, read reference.md — consult it when a rule needs interpretation or when you face a non-obvious design decision.
Core Rules
1. Leave the code cleaner
Every change must improve at least one of: clarity, naming, simplicity, cohesion, testability, error handling, duplication removal, or separation of concerns. Do not add code that is merely functional — add code that is understandable.
2. Optimize for readers
- Write code for the next engineer, not for impressiveness.
- Prefer straightforward code over clever code.
- Keep control flow obvious.
- If code is hard to explain, treat that as a design problem.
3. Use strong names
- Names must reveal intent. Use domain language consistently.
- Prefer specific names over generic ones. Avoid
data,info,thing,stuff,manager,helper,util,misc,handle,temp,objunless they are genuinely correct in the domain or an external protocol. - Boolean names read like predicates (
active?,isActive,hasItems,retryable?), following the language's convention. - Collection names are plural.
- Function names describe the action performed, not vague activity
(
calculate_invoice_total, notdo_invoice).
4. Keep methods small and focused
- A method should do one thing at one level of abstraction.
- Do not mix business rules, formatting, persistence, external calls, and error recovery in one method. Extract helpers when a method grows multiple phases.
- Prefer zero, one, or two parameters; three should trigger scrutiny; more usually means a missing value object or domain object.
- Do not use boolean parameters to switch behavior when separate methods would express intent more clearly.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 145 lines · 93 tokens per session scan A c8a9d0ede73b
clean-code is a skill published in the GitHub repository superplanehq/superplane (5,633 stars, last pushed yesterday), licensed Apache-2.0. It adds 93 tokens to every session and 1,280 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
iterate-pr
Iterate on a PR until CI passes. Optionally merge or merge and publish a release of the repo. Automates the feedback-fix-push-wait cycle.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
database-schema-designer
Design robust, scalable database schemas for SQL and NoSQL databases. Provides normalization guidelines, indexing strategies, migration patterns, constraint design, and performance optimization. Ensures data integrity, query performance, and maintainable data models.
gen-relationship
Create and refine schema-backed Meshery relationship definitions (models//relationships/.json). Use for "add a relationship", "fix this relationship JSON", classifying kind/type/subType, or reviewing selectors and mutatorRef/mutatedRef patches between model components.
gepetto
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
gnhf
Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.