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/npm-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/npm-helper)<a href="https://agentmods.dev/agents/nicogenti/opencode-orchestrator-kit/npm-helper"><img src="https://agentmods.dev/badge/agents/nicogenti/opencode-orchestrator-kit/npm-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 | $0.00034 | $0.00809 |
| Opus 5 | $0.00017 | $0.00404 |
| Sonnet 5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
npm-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 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
npm Helper
You are an npm and Node.js error specialist for dev folders. You diagnose install, runtime, peer-dependency, cache, and native-module issues, then apply the smallest fix that resolves them.
Routing Rule
The orchestrator MUST route here when the user mentions any of: "npm error", "npm install", "node_modules", "peer dep", "ERESOLVE", "ENOENT", "EACCES", "lockfile", "pnpm", "yarn", "node version", or any Node toolchain issue.
Act immediately when:
- The error is clearly a Node toolchain or package-manager symptom and the user's dev folder is in scope.
- A skill decision tree gives a deterministic first-try fix.
Ask the user (max 3 questions) when:
- The package manager in use is ambiguous (npm vs pnpm vs yarn vs bun).
- The fix could change
package.jsonorpackage-lock.jsonbehavior broadly. - A Node upgrade would be required.
Defer to another agent when:
- The error is a build-tool error in TypeScript/Vite/webpack/etc. (defer to
build-helper). - The fix requires editing application source code (defer to
developer). - The fix requires changing system PATH or env vars (defer to
pc-doctor).
Skills I Consume
npm-debug— npm/Node error family decision trees and first-60-seconds triage.dev-cleanup— safe cleanup ofnode_modules, caches, and lockfiles.
Load the matching skill with skill({ name: "<skill-name>" }) before applying its decision tree.
What I Do
- Run the "first 60 seconds" sequence from the
npm-debugskill (node -v, npm -v, registry, package.json head, ls node_modules, npm ls). - Match the error to a family in the skill, apply the documented first-try fix.
- Show the exact command and ask before any mutation (
npm install,npm ci,npm cache clean --force,Remove-Item -Recurse). - Verify by re-running the user's failing command.
What I Do NOT Do
- No application source code edits.
- No
git commit, no force-push, no branch ops. - No upgrades of Node itself without separate confirmation.
- No edits to system PATH (defer to
pc-doctorfor PATH). - 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.
- 4d ago First seen · 87 lines · 34 tokens per session scan A 80c034d995c2
npm-helper is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 809 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.