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 commands/superplanehq/superplane/component-review.rulesgit 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/commands/superplanehq/superplane/component-review.rules)<a href="https://agentmods.dev/commands/superplanehq/superplane/component-review.rules"><img src="https://agentmods.dev/badge/commands/superplanehq/superplane/component-review.rules.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 | $0.00000 | $0.01603 |
| Opus 5 | $0.00000 | $0.00801 |
| Sonnet 5 | $0.00000 | $0.00321 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
component-review.rules 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 4d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Component Review Rules
Add new rules to this list in the same format. Keep each rule focused and testable. Categories define ordering and scope.
Product functionality
Focus on externally visible behavior in the UI, not internal function details.
Registration
The component is registered in the application.
For core compoents: with registry.RegisterComponent
For integrations: listed in the integration's Components() or Triggers() output.
Naming
- For core components: uses the same name as the registration name
- For integration components: name should follow the format
<integration>.<name>, e.g.github.getIssuevsgithub.GetIssue - A component name should always use camel-case, and should never contain spaces, or underscore
- If the component is a trigger, it should start with
on - Trigger names should use the resource names that they reference, not actions, unless the trigger itself is about an specific action. For example,
github.onIssueCommentinstead ofgithub.onIssueCommented
Label
- The component label shown in the UI is non-empty and human-readable
- Uses Title Case
- No raw slug casing
Description
The component description shown in the UI is non-empty, user-facing. Short, clear and concise.
Documentation
- The component documentation shown in the UI is non-empty.
- It is valid markdown
- If it uses titles, the biggest level should be ##
Icon
- The component icon shown in the UI is non-empty and maps to a valid UI icon
- Either Lucide Icon slug
- Or an existing custom asset
Color
The component color shown in the UI is non-empty and consistent with existing component color usage.
Example output
- The example output shown in the UI embeds an example
- JSON file (e.g.,
example_output.json). - Example JSON files are valid and match the emitted payload structure.
Configuration fields
- Every configuration field shown in the UI has a:
Name,Label,Type, andDescription - Required fields are marked
Required: true. - Required fields should always be placed before optional fields
- When possible, configuration never asks users to enter IDs that aren't easily available to them (e.g., requiring a Discord channel ID).
- When users can choose from existing resources (e.g., a GitHub repository), always use
FieldTypeIntegrationResource. Example: instead of having achannelIdfield of typeFieldTypeString, use aFieldTypeIntegrationResourceconfiguration field. - For trigger filters and component configuration that use equality, non-equality, or regex matching, prefer
configuration.FieldTypeAnyPredicateListand match values viaconfiguration.MatchesAnyPredicate. Avoid ad-hoc wildcard or comma parsing unlessany-predicate-listcannot express the requirement. Ifconfiguration.FieldTypeAnyPredicateListcannot meet your requirements, look for ways to extend it before developing a specific implementation. - if filters are part of the trigger, we should always have a default filter for the most common use case. That makes it easier for the user to configure it, and we don't produce unnecessary events to the system. For example, the default
github.onPushrefs filter is for commits on the main branch.
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.
- 4d ago First seen · 128 lines · 0 tokens per session scan A 543c435b615d
component-review.rules is a command published in the GitHub repository superplanehq/superplane (5,731 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,603 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 2026-08-30.
Other commands, from other repositories
fix-pr-review-comments
Analyze PR comments, implement fixes, and post targeted responses.
generate
Re-generate Squad agent definitions as your plan evolves.
bmad-party-mode
Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a party, define personas, or build an AI focus-group panel.
ark-create-crd
You are an expert Kubernetes CRD developer working on the ARK project. Your task is to generate a new Custom Resource Definition following ARK's established patterns and design guidelines.
define-events
Produces instrumentation specification with events, properties, owners, and QA steps.
hypothesis
Generate hypotheses and define how to test them.