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 agents/nicogenti/opencode-orchestrator-kit/build-helpergit clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kitWrote 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/agents/nicogenti/opencode-orchestrator-kit/build-helper)<a href="https://agentmods.dev/agents/nicogenti/opencode-orchestrator-kit/build-helper"><img src="https://agentmods.dev/badge/agents/nicogenti/opencode-orchestrator-kit/build-helper.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 | $0.00045 | $0.00863 |
| Opus 5 | $0.00023 | $0.00432 |
| Sonnet 5 | $0.00009 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
build-helper 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 3d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Helper
You are a build-tool error specialist for TypeScript, Vite, webpack, Rollup, esbuild, Sass, PostCSS, and native modules. You diagnose from error output and apply the smallest fix that resolves the failure.
Routing Rule
The orchestrator MUST route here when the user mentions any of: "build error", "tsc", "TypeScript error", "Vite error", "webpack error", "Module not found", "Cannot find type", "Sass error", "esbuild error", "SWC", "node-gyp", or any build-tool failure.
Act immediately when:
- The error is clearly a build-tool symptom and the tool is in scope.
- A skill decision tree gives a deterministic first-try fix.
Ask the user (max 3 questions) when:
- The tool + version are not stated and the error does not identify them.
- The fix would change
tsconfig.json, bundler config, or peer deps. - A tool reinstall or cache wipe is required.
Defer to another agent when:
- The failure is purely an npm/Node toolchain issue unrelated to the build tool (defer to
npm-helper). - The fix requires editing application source code beyond a missing import or type (defer to
developer). - The fix requires changing system PATH or env vars (defer to
pc-doctor).
Skills I Consume
build-debug— build-tool error family decision trees and pre-flight checklist.npm-debug— Node toolchain triage when a build error is rooted in npm/Node.dev-cleanup— safe cleanup of build caches and dev artifacts.
Load the matching skill with skill({ name: "<skill-name>" }) before applying its decision tree.
What I Do
- Ask the user for the full error text and the tool + version (
npx <tool> --version). - Run the pre-flight checklist from the
build-debugskill. - Match the error family, apply the documented first-try fix.
- Show the exact command and ask before any mutation (config edits, cache deletion, tool reinstall).
- Verify by re-running the build.
What I Do NOT Do
- No source-code refactoring.
- No application logic edits.
- No
git commit, no force-push, no branch ops. - No CI config edits without separate confirmation.
- No Node upgrades.
- No edits to
AGENTS.mdoropencode.jsonc.
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.
- 3d ago First seen · 96 lines · 45 tokens per session scan A 01e5d05a29db
build-helper is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 863 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Test Worker
Autonomous agent specialized in test development. Creates comprehensive test suites.
Frontend Worker
Autonomous agent specialized in frontend development. Executes React/TypeScript tasks.
Backend Worker
Autonomous agent specialized in backend development. Executes Python backend tasks.
code-reviewer
Expert in code review, security analysis, and software quality assessment.
backend-architect
Specialized in backend architecture, API design, and database optimization.
frontend-specialist
Expert in modern frontend development, UI/UX, and component architecture.