stage-6-implementation

stage-6-implementation is a skill for Claude Code from cdeust/ai-architect-mcp. It costs 5 tokens per session (2,135 once invoked), scanned A, original, MIT.

An implementation coordinator for turning a product requirements document into code changes. It assigns file-level work to separate workers, combines their results, and checks that the integrated project builds and matches the requirements.

In plain words
What is it for?
Breaking down implementation work, coordinating workers, integrating their changes, and checking build and requirement coverage.
Why use it?
It organizes large implementations and keeps code and tests linked to stated requirements.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-architect plugin — 13 skills, 4 commands, 2 MCP servers, 1 plugin shipped together

Good fit Breaking down implementation work, coordinating workers, integrating their changes, and checking build and requirement coverage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cdeust/ai-architect-mcp/stage-6-implementation
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.

Any agent
npx skills add cdeust/ai-architect-mcp --skill stage-6-implementation
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp

Made for: Claude Code.

Or install ai-architect, the plugin that ships this one along with the rest of its 13 skills, 4 commands, 2 MCP servers, 1 plugin.

Wrote 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.

agentmods badge for stage-6-implementation

README.md
[![agentmods](https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/stage-6-implementation.svg)](https://agentmods.dev/skills/cdeust/ai-architect-mcp/stage-6-implementation)
Your own site
<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp/stage-6-implementation"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/stage-6-implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00005 $0.02135
Opus 5 $0.00003 $0.01068
Sonnet 5 $0.00001 $0.00427
Haiku 4.5 $0.00001 $0.00214

Measured 7d ago against content hash edb4171de09e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

stage-6-implementation 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 7d 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.

skills/stage-6-implementation/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Allostatic Priming

You are the implementation orchestrator. You break the PRD into file-level tasks, spawn a worker per file, and synthesise. You do not write code yourself — you coordinate workers and verify their integration. Every file produced must trace back to a PRD requirement. Every test must trace back to an acceptance criterion.

Trigger

USE WHEN: implement, write code, create branch, code generation, build feature, file-level tasks, orchestrator-workers, git branch, task decomposition, worker coordination NOT FOR: verify — stage 7, PRD review — stage 5, anything pre-implementation

Survival Question

"Have all files in the PRD change manifest been implemented by dedicated workers, and does the integrated result compile?"

Before you start

  1. ai_architect_load_context(stage_id=5, finding_id="{findingID}") — load verification report (confirms PRD passed review)
  2. ai_architect_load_context(stage_id=4, finding_id="{findingID}") — load PRD files (prd-technical.md for file manifest, prd-tests.md for test specs)
  3. ai_architect_load_context(stage_id=3, finding_id="{findingID}") — load integration design (composition root wiring)
  4. ai_architect_load_session_state(session_id="{sessionID}") — confirm currentStage = 6, check retryCount
  5. ai_architect_list_experience_patterns(stage_id=6, min_relevance=0.1) — load solution patterns for implementation context

Missing Stage 5 verification report = BLOCK. Cannot implement without reviewed PRD.

Input contract

Field Type Source Required
stage-5-verification-report.json JSON StageContext[stage-5] YES — BLOCK if missing
prd-technical.md MD StageContext[stage-4] YES — file change manifest
prd-tests.md MD StageContext[stage-4] YES — test specifications
prd-acceptance.md MD StageContext[stage-4] YES — acceptance criteria
stage-3-integration-design.md MD StageContext[stage-3] YES — composition root wiring
ExperiencePatterns list ai_architect_list_experience_patterns NO — enrichment

Read the full file on GitHub · 240 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. 7d ago First seen · 240 lines · 5 tokens per session scan A edb4171de09e

Subscribe to this mod's changes

stage-6-implementation is a skill published in the GitHub repository cdeust/ai-architect-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 2,135 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens

hive.pdf

Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…

aden-hive/hive · 98 tokens

hive.note-taking

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

aden-hive/hive · 30 tokens

sdlc-accelerate

End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.

jmagly/aiwg · 23 tokens