implementation-engineer

A technical design agent for approved software requirements. It creates architecture, API, database, security, decision, and testing documents.

In plain words
What is it for?
Use it during the design phase to define system components, data models, APIs, security threats, architecture decisions, and design-time tests.
Why use it?
It turns requirements into detailed technical plans that developers can implement and review.

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/baodq97/open-plugin/implementation-engineer
Clone the repo
git clone --depth 1 https://github.com/baodq97/open-plugin
Per session 347 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,716 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 $0.00347 $0.02716
Opus 5 $0.00173 $0.01358
Sonnet 5 $0.00069 $0.00543
Haiku 4.5 $0.00035 $0.00272

Measured yesterday against content hash d47f43b5d1ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation-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 yesterday.

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/vbounce/agents/implementation-engineer.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CONTRACT

Input (MANDATORY — read these files BEFORE any work)

File Path Required
Architecture Design {workspace}/design/design.md YES
API Specification {workspace}/design/api-spec.md YES
Database Schema {workspace}/design/database-schema.md YES
Security Design {workspace}/design/security-design.md YES
Test Specifications {workspace}/design/test-specifications.md YES
Contracts {workspace}/contracts/contracts.* YES
API Surface {workspace}/contracts/api-surface.yaml YES
Test Plan {workspace}/contracts/test-plan.yaml YES
Requirements {workspace}/requirements/requirements.md YES
Test Skeletons {workspace}/requirements/test-skeletons.md YES
Tech Context {workspace}/tech-context.yaml YES
Tech Context Prompt {workspace}/tech-context-prompt.md NO
Cycle State {workspace}/state.yaml YES
Learned Rules .claude/rules/vbounce-learned-rules.md NO
Project Config .claude/vbounce.local.md NO

Output (MUST produce ALL of these)

File Path Validation
Implementation Summary {workspace}/implementation/summary.md Lists all files created/modified
Package Verification {workspace}/implementation/package-verification.md 0 hallucinated packages
Test Report {workspace}/implementation/test-report.md Distribution stats, V-Model levels
Coverage Matrix {workspace}/implementation/coverage-matrix.md Every AC mapped to >= 1 test
Execution Report {workspace}/implementation/execution-report.md Compile + test results per iteration
Source Code Project source directories Follows project conventions
Test Suite Project test directories Tests runnable with project test framework

References (consult as needed)

  • references/coding-standards.md — Naming, structure, documentation
  • references/hallucination-patterns.md — Known fake packages and APIs
  • references/edge-cases.md — Edge case checklist
  • references/id-conventions.md — ID format standards

Read the full file on GitHub · 223 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. yesterday First seen · 223 lines · 347 tokens per session scan A d47f43b5d1ae

Subscribe to this mod's changes

implementation-engineer is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 347 tokens to every session and 2,716 once invoked, about $0.0017 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.