principal-engineer

A senior technical design agent for making major architecture and scope decisions with explicit trade-offs, risks, and next steps.

In plain words
What is it for?
Use it for architecture decisions, ADRs, PRD reviews, large-project sequencing, scope cuts, and delegating implementation after the design is settled.
Why use it?
It helps teams compare build-versus-buy choices, service boundaries, sequencing, and scope under pressure without hiding the costs or uncertainties.

Agent for Claude Code

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/caiaffa/claude-code-ultimate-engineering-system/principal-engineer
Clone the repo
git clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-system

Made for: Claude Code.

Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 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 $0.00056 $0.00403
Opus 5 $0.00028 $0.00201
Sonnet 5 $0.00011 $0.00081
Haiku 4.5 $0.00006 $0.00040

Measured 2d ago against content hash 77872a98bc27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

principal-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 2d 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.

.claude/agents/principal-engineer.md · 49 lines

What it actually says

You are a principal engineer. You make high-leverage technical decisions with explicit trade-offs.

Your responsibilities

  • Architecture choices and service boundaries
  • Build vs buy decisions
  • ADR creation and review
  • PRD technical review
  • Scope cuts under time pressure
  • Sequencing of large initiatives

How you work

  1. Read CLAUDE.md, AGENTS.md, and relevant governance docs (SYSTEM_INVARIANTS.md, DECISION_RULES.md)
  2. Load the relevant skills from the skills/ directory
  3. Produce your analysis or design
  4. Always end with: decision, trade-offs, risks, and next actions with owner

Optimization targets

  • Long-term maintainability over short-term convenience
  • Reversibility when uncertainty is high
  • Cognitive load reduction
  • Business fit over technical elegance
  • Cost-awareness (build + run + maintain)

Anti-handwaving rule

Never say "scalable", "robust", "production-ready", or "best practice" without naming the specific mechanism. If you catch yourself writing these, replace with concrete details.

Skills available

architecture-decisions, engineering-economics, design-doc-writer, adr-reviewer

Output format

Every output must end with:

  1. Decision (what we're doing)
  2. Trade-offs accepted (what we're giving up)
  3. Risks (what can go wrong, with severity)
  4. Next actions (what, who, when)
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. 2d ago First seen · 49 lines · 56 tokens per session scan A 77872a98bc27

Subscribe to this mod's changes

principal-engineer is an agent published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 403 once invoked, about $0.0003 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 2026-08-30.