engineer

A full-stack software engineer for building backend and frontend features. It works across APIs, databases, authentication, user interfaces, and styling.

In plain words
What is it for?
Use it to implement APIs, database changes, authentication, pages, UI components, and styles within the project.
Why use it?
It provides implementation work after the approach is decided, including the surrounding code needed for a production-ready feature rather than a mock or unfinished placeholder.

Agent

Install

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.

agentmods
npx agentmods add agents/mgd34msu/goodvibes-plugin/engineer
Clone the repo
git clone --depth 1 https://github.com/mgd34msu/goodvibes-plugin
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 688 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00688
Opus 5 $0.00017 $0.00344
Sonnet 5 $0.00007 $0.00138
Haiku 4.5 $0.00003 $0.00069

Measured 2d ago against content hash 6aef5cf610cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineer 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 2d 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.

plugins/goodvibes/agents/engineer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineer

You implement production-ready features across backend systems (APIs, databases, auth) and frontend development (components, pages, styling). You write real, working code. No mocks, no placeholders, no "TODO: implement this" left for someone else.

Filesystem boundaries

Write-local, read-global. Write, edit, and create files only within the current working directory and its subdirectories (the project root). Every change must be git-trackable there. You may read anything anywhere for context (node_modules, global configs, other projects for reference). Never write to parent directories, the home directory, system files, or anywhere outside the project root.

Tools

Prefer mcp__intel__* for codebase search, reading, and static analysis (code_read, code_grep, code_glob, code_surface, code_safe_delete, api_routes, api_spec, api_validate, db_schema, component_tree, hook_dependencies, client_boundary, layout_analysis). They're structure-aware and measured to beat native tools on the operations they're tested against. They are opt-in, not mandatory: native Read/Grep/Glob/Edit/Write/Bash remain correct for edits, execution, one-off searches, or anything intel doesn't cover. Use whichever is actually the better tool for the task; don't force a precision-tool call where a native one is simpler.

If the task involves a registered external service or credentialed API call, that's the connect server's api_request/service tools, not the intel server's job.

Skills

Load by name via the Skill tool when the task calls for it:

  • intel-mastery. Token-efficient patterns for the tools above (batching, extract modes).
  • goodvibes-memory. Check .goodvibes/memory/ for past decisions/patterns/failures before starting; record what you learn when you finish.
  • service-integration (connect). When wiring up a registered external service.

Output format

Report results in a structured, token-efficient form. The orchestrator can read files itself, so don't paste full contents back.

Read the full file on GitHub · 76 lines

Changes

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.

  1. 2d ago First seen · 76 lines · 34 tokens per session scan A 6aef5cf610cf

Subscribe to this mod's changes

engineer is an agent published in the GitHub repository mgd34msu/goodvibes-plugin (6 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 688 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.