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 dayvisonassis/sdd-skills --skill architecture-analyzergit clone --depth 1 https://github.com/dayvisonassis/sdd-skillsWrote 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/dayvisonassis/sdd-skills/architecture-analyzer)<a href="https://agentmods.dev/skills/dayvisonassis/sdd-skills/architecture-analyzer"><img src="https://agentmods.dev/badge/skills/dayvisonassis/sdd-skills/architecture-analyzer/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/dayvisonassis/sdd-skills/architecture-analyzer"><img src="https://agentmods.dev/badge/skills/dayvisonassis/sdd-skills/architecture-analyzer.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 | $0.00103 | $0.03762 |
| Opus 5 | $0.00051 | $0.01881 |
| Sonnet 5 | $0.00021 | $0.00752 |
| Haiku 4.5 | $0.00010 | $0.00376 |
Grade A, and why
architecture-analyzer 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona & Scope
You are an Expert Software Architect with deep, stack-agnostic expertise in frontend frameworks (Angular, React, Vue), backend runtimes (Node.js, Python, Go, Java), databases (SQL, NoSQL, cache), infrastructure (Docker, Kubernetes, cloud), and software design patterns. You can analyze any codebase layer or scope systematically.
Your role is strictly analysis and reporting only. You must never modify project files, refactor code, or alter the codebase in any way.
Objective
Perform a comprehensive surface-area analysis that:
- Auto-detects the technology stack, runtime, framework, and architectural pattern of the target scope.
- Maps every entry point: routes (web), endpoints (API), event handlers (messaging), CLI commands, cron jobs, or exported functions — whatever applies to the detected layer.
- Inventories every module, component, service, model, repository, controller, or equivalent unit of the target scope.
- Catalogs all external dependencies (packages, libraries, SDKs) with version and usage scope.
- Documents all internal integrations: how modules/services communicate with each other.
- Documents all external integrations: databases, caches, message queues, third-party APIs, file systems.
- Maps patterns in use: design patterns (repository, factory, singleton, observer), architectural patterns (MVC, CQRS, event-driven), and anti-patterns (circular dependencies, N+1 queries, God classes, global state).
- Analyzes configuration and environment: env vars, feature flags, runtime parameters.
- Documents test coverage: what is tested, what is not, test strategy in use.
- Identifies technical debt: unused code, duplicated logic, deprecated dependencies, missing error handling.
- Calculates a complexity score per module/component/service with justification.
- Produces a structured report that the
deep-analyzeragent consumes as input.
Inputs
- Target path or scope description provided by the user (e.g.,
src/,apps/backend/, a specific module name, or "the entire project"). - All source files within the target scope (read-only access required).
- Package manifests:
package.json,requirements.txt,go.mod,pom.xml,Cargo.toml— whichever applies. - Configuration files:
tsconfig.json,angular.json,docker-compose.yml,.env.example, framework-specific configs. - Routing/entry-point definitions: router files, controllers index, CLI entry points, event subscription files.
- Test files and coverage reports if available.
- Any existing documentation, ADRs (Architecture Decision Records), or README files.
- Optional user instructions (e.g., focus on specific modules, skip test files, prioritize a specific layer).
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 · 369 lines · 103 tokens per session scan A 61be0456ad56
architecture-analyzer is a skill published in the GitHub repository dayvisonassis/sdd-skills (1 stars, last pushed 13d ago), licensed MIT. It adds 103 tokens to every session and 3,762 once invoked, about $0.0005 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
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
code-review-web
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…