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 int2t05/engineering-skills --skill architecturegit clone --depth 1 https://github.com/int2t05/engineering-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/int2t05/engineering-skills/architecture)<a href="https://agentmods.dev/skills/int2t05/engineering-skills/architecture"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/architecture/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/int2t05/engineering-skills/architecture"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/architecture.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 | $0.00024 | $0.00512 |
| Opus 5.5 | $0.00010 | $0.00205 |
| Sonnet 5.5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
architecture 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 15d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture
When to use
- Design or audit system boundaries and consequential technical decisions.
Not for: spec for behavior; codebase-design for existing module boundaries.
Steps
-
Extract confirmed behavior, real constraints and operational context; do not invent quality thresholds.
-
Investigate comparable implementations and current official docs for consequential choices; compare complexity, failure modes and operating costs.
-
Define components, trust boundaries, ownership, contracts and recovery using the simplest adequate architecture.
-
Record significant decisions and rejected alternatives; prepare TECH and risk-based human review before dependent implementation.
Output: Suggested paths, subject to human audit: docs/TECH.md; optionally docs/vX.Y/tech.md and docs/design/adr/NNNN-slug.md.
Verify
- Boundaries and failure paths fit requirements; significant decisions have evidence, trade-offs and review criteria.
References
- engineering-principles.md — shared decision boundaries, scope and verification.
- mermaid-diagrams.md — Mermaid syntax for architecture diagrams
- references/tech-audit-guide.md — reference-first discipline, the audit→confirm→revise→mature lifecycle, and the TECH-doc AUD catalog with table formats
- references/nfr-checklist.md — NFR categories (scalability, performance, availability, security, reliability, cost) with targets
- references/architecture-patterns.md — pattern comparison (monolith, microservices, event-driven, CQRS, serverless)
- references/database-selection.md — database types and decision matrix
- references/system-design.md — full system design template
- references/adr-template.md — ADR format, example, and naming convention
- references/error-resilience.md — throw-vs-return, error propagation, retry/circuit-breaker, idempotency, fallback UX, error-to-message mapping
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago Changed · -92 lines · +24 tokens per session 1bbbb2884b0a
- 21d ago Changed · +33 lines · -64 tokens per session eac108624211
- 2mo ago First seen · 102 lines · 64 tokens per session scan A 1c089e2cfbe7
architecture is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 15d ago), licensed MIT. It adds 24 tokens to every session and 512 once invoked, about $0.0001 per session on Opus 5.5. 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
design-reviewer
Use after AC and before RED for any wave that ships UI or changes existing behaviour. Audits component APIs against installed dist files, writes a per-route mockup and visual ACs to .wave/dr.md.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
plan
Analyzes architecture, selects patterns, assesses testability, then decomposes work into ordered TDD tasks with exact verification commands and explicit acceptance mapping. Works from an approved spec (zuvo:brainstorm output) or directly from a user-provided description.
Eval-Driven Skill Design
A review guide for new coding-agent skills that checks whether each skill has both examples it should catch and examples it should ignore, plus evaluation setup.
pr-workflow
Crear pull requests completas con descripcion, labels y reviewers.
Component Test Scaffold (Next.js)
Generate React/Next.js component test skeletons (RTL) from specifications.