SuperPlane is an open-source automation system that turns selected software backlog issues into pull requests by coordinating coding agents, source control, testing, review, and approvals. Engineering teams use it to automate routine development work while keeping ambiguous decisions for humans, and the catalogue add-ons support its workflows.
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/ui-copynpx skills add superplanehq/superplane --skill ui-copygit clone --depth 1 https://github.com/superplanehq/superplaneWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/superplanehq/superplane/ui-copy)<a href="https://agentmods.dev/skills/superplanehq/superplane/ui-copy"><img src="https://agentmods.dev/badge/skills/superplanehq/superplane/ui-copy.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00072 | $0.01419 |
| Opus 5 | $0.00036 | $0.00709 |
| Sonnet 5 | $0.00014 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
ui-copy 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 5d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Copy
Write interface copy as part of the design, not as decoration after the layout is done. The product is speaking to someone who is trying to complete a task.
Adapted from Operately's ui-copy skill for SuperPlane product vocabulary.
Language: Write all user-facing strings in ASD-STE100 Simplified Technical English style. Follow simplified-technical-english together with this skill. If UX tone and STE conflict, choose the clearer STE wording.
Workflow
- Identify the user's current goal, screen state, and likely concern.
- Find nearby existing copy and match the product vocabulary, casing, tense, and tone.
- Draft the clearest STE version first. Prefer plain, specific, task-oriented language over personality.
- Tighten the copy until every word has a job (≤20 words for instructions, ≤25 for descriptions).
- Check that buttons, links, errors, and helper text set accurate expectations.
- If changing existing copy, scan adjacent screens or components for terms that should stay consistent.
Principles
- Treat words as UI. Real copy belongs in early designs, prototypes, and implementation; do not rely on placeholder text when the wording affects comprehension, trust, or layout.
- Clarity beats brevity and personality. Short is good only when it remains specific. Do not use cute, clever, or branded wording when it can hide the action.
- Write for the user in this moment. Ask what they are trying to do, what they need to know now, what can wait, and whether they need reassurance.
- Be honest and concrete. Avoid marketing adjectives, hype, vague promises, and copy that tells users how to feel.
- Use STE plain language. Avoid jargon, unexplained acronyms, idioms, contractions, internal names, and technical error codes unless the user can act on them.
- Prefer active voice, imperative or simple present, and specific verbs:
Create,Save,Archive,Invite,Download,Connect. - Keep copy scannable. Use short sentences, front-load important words, and reveal advanced detail only when needed.
- Keep vocabulary consistent. Do not alternate between terms like
canvas,workflow, andpipelineunless the product treats them as different concepts. - Match the platform and interaction. Use
tapfor touch surfaces andclickonly where pointer interaction is the assumption. - Do not use humor in UI copy. Never use humor in high-friction, high-risk, error, payment, privacy, or destructive flows.
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.
- 5d ago First seen · 125 lines · 72 tokens per session scan A 22ac6dbac06d
ui-copy is a skill published in the GitHub repository superplanehq/superplane (5,731 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,419 once invoked, about $0.0004 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
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.
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.
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.
agent-md-refactor
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.