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 skills add ballerina-platform/ballerina-vscode --skill agent-buildergit clone --depth 1 https://github.com/ballerina-platform/ballerina-vscodeWrote 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/ballerina-platform/ballerina-vscode/agent-builder)<a href="https://agentmods.dev/skills/ballerina-platform/ballerina-vscode/agent-builder"><img src="https://agentmods.dev/badge/skills/ballerina-platform/ballerina-vscode/agent-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ballerina-platform/ballerina-vscode/agent-builder"><img src="https://agentmods.dev/badge/skills/ballerina-platform/ballerina-vscode/agent-builder.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.05961 |
| Opus 5.5 | $0.00000 | $0.02384 |
| Sonnet 5.5 | $0.00000 | $0.01192 |
| Haiku 4.5 | $0.00000 | $0.00596 |
Grade A, and why
agent-builder scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
and they have to test it with another client, such as curl. How it starts
The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Builder
The agent diagram is not generated from a model, it is parsed directly out of the source you write. Code that compiles but does not match the shapes below still renders as an incomplete or empty agent, and the user cannot then edit it from the low-code side. Follow every rule.
<...> marks a placeholder to substitute from the user's request. Never emit it literally.
Derive identifiers from the agent's purpose in camelCase, and keep the family consistent:
<agent>Agent, <agent>Model, <agent>Listener. Service paths are the exception, they are
kebab-case, written <agent-name>.
System prompt: always inline
The system prompt MUST be an inline mapping constructor in the ai:Agent construction. A prompt
assigned to a separate variable and referenced by name is not read at all, the agent card renders
with no role and no instructions.
Both role and instructions MUST use the string backtick template so multi-line text survives
a round trip.
Correct:
final ai:Agent <agent>Agent = check new (
systemPrompt = {
role: string `<short role name>`,
instructions: string `<first line of instructions>
<continuation line, starting at column 0>
<continuation line, starting at column 0>`
}, model = <agent>Model, tools = [<toolName>, <toolName>]
);
Do not indent the continuation lines of instructions to match the surrounding code, the leading
whitespace is part of the string and is shown to the user in the prompt editor. Start every
continuation line at column 0, as above.
Model provider: declare the concrete type
Every ai component is identified in the diagram by its declared type, so always declare the
concrete class. An abstract type renders as an unresolved node.
final ai:Wso2ModelProvider <agent>Model = check ai:getDefaultModelProvider();
ai:Wso2ModelProvider not ai:ModelProvider; ai:Wso2EmbeddingProvider not
ai:EmbeddingProvider; ai:InMemoryVectorStore not ai:VectorStore. When the user names a
provider (OpenAI, Azure, Anthropic, Ollama, …) declare that provider's own class, same rule.
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.
- today Changed · +8 lines 7abae1e0789e
- 3d ago First seen · 508 lines · 0 tokens per session scan A 6e11288cc99a
agent-builder is a skill published in the GitHub repository ballerina-platform/ballerina-vscode (49 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,961 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
erlang-otp-behaviors
Use when oTP behaviors including genserver for stateful processes, genstatem for state machines, supervisors for fault tolerance, genevent for event handling, and building robust, production-ready Erlang applications with proven patterns.
axiom-concurrency
Use when writing ANY async code, actors, or threads in an Apple-platform app, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.
haskell-pro
Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.