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 skills add cdeust/ai-architect-mcp --skill stage-3-integrationgit clone --depth 1 https://github.com/cdeust/ai-architect-mcpWrote 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/skills/cdeust/ai-architect-mcp/stage-3-integration)<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp/stage-3-integration"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/stage-3-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp/stage-3-integration"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/stage-3-integration.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00005 | $0.02135 |
| Opus 5 | $0.00003 | $0.01068 |
| Sonnet 5 | $0.00001 | $0.00427 |
| Haiku 4.5 | $0.00001 | $0.00214 |
Grade A, and why
stage-3-integration 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 9d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Allostatic Priming
You are a software architect designing the seam where this change meets the existing system. Hexagonal architecture. Ports and adapters. You identify the affected ports, the adapters to change, and the composition root wiring required. You do not implement — you design the integration blueprint.
Trigger
USE WHEN: integration design, architecture design, affected ports, adapter design, cross-engine, hexagonal, composition root, port inventory, seam analysis, interface design NOT FOR: plan interview, PRD generation, impact analysis — stage 2, implementation — stage 6
Survival Question
"Do I have a complete list of affected ports, adapters, and composition root changes — with no circular dependency introduced?"
Before you start
MANDATORY: Load ALL required upstream artifacts.
ai_architect_load_context(stage_id=0, finding_id="{findingID}")— load Stage 0 health report (codebase intelligence engine availability)ai_architect_load_context(stage_id=1, finding_id="{findingID}")— load Stage 1 findingsai_architect_load_context(stage_id=2, finding_id="{findingID}")— load Stage 2 impact map (propagation paths, affected engines)ai_architect_load_session_state(session_id="{sessionID}")— confirm currentStage = 3ai_architect_list_experience_patterns(stage_id=3, min_relevance=0.1)— load architecture decisions for context
If codebase_intelligence: "ai_codebase_intelligence" in Stage 0 health report:
6. ai_architect_codebase_cypher(query="MATCH (a)-[:CodeRelation {type: 'IMPLEMENTS'}]->(b) WHERE b.name IN {affected_ports} RETURN a.name, a.filePath", repo="{target_repo}") — find existing adapter implementations
7. ai_architect_codebase_context(name="{affected_port}", include_content=true, repo="{target_repo}") — for each affected port from impact map
Missing Stage 2 impact map = BLOCK. Cannot design integration without knowing blast radius.
Input contract
| Field | Type | Source | Required |
|---|---|---|---|
stage-2-impact-map.json |
JSON | StageContext[stage-2] | YES — BLOCK if missing |
| ImpactMap.affectedEngines | list | Stage 2 output | YES |
| Port/interface definitions | files | Codebase (discovered via search) | YES — need to cross-reference |
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.
- 9d ago First seen · 221 lines · 5 tokens per session scan A 402ebd509bd4
stage-3-integration 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.
Other skills, from other repositories
api-design-reviewer
Use when reviewing a PR that adds or changes API endpoints, auditing an existing API for v2 migration, or establishing REST API standards. Triggers on "API review", "REST design review", "breaking change check", "OpenAPI audit", "endpoint review", or "API consistency".
backend-service
Use when a ticket asks for backend business logic that isn't itself an endpoint or a migration — a service/use-case, a domain operation, a background job, or orchestration across repositories. Invoke for "add a service to do X", "implement the use-case", or "extract the business logic out of the handler".
add-api-endpoint
Use when a ticket asks to add or extend an HTTP/API endpoint — a new route, handler, or RPC method — with request validation and a defined response. Invoke for "add a POST /things endpoint", "expose a list API", or "add a field to the X response".
oauth-expert
OAuth 2.0 and OpenID Connect expert for authorization flows, PKCE, and token management.
openapi-expert
OpenAPI/Swagger expert for API specification design, validation, and code generation.
graphql-expert
GraphQL expert for schema design, resolvers, subscriptions, and performance optimization.