Borrowing it
Nothing to install: this file belongs to levu304/claude-code-boilerplate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/levu304/claude-code-boilerplate/main/.claude/agents/principal-engineer.mdgit clone --depth 1 https://github.com/levu304/claude-code-boilerplateWrote 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/agents/levu304/claude-code-boilerplate/principal-engineer)<a href="https://agentmods.dev/agents/levu304/claude-code-boilerplate/principal-engineer"><img src="https://agentmods.dev/badge/agents/levu304/claude-code-boilerplate/principal-engineer/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/agents/levu304/claude-code-boilerplate/principal-engineer"><img src="https://agentmods.dev/badge/agents/levu304/claude-code-boilerplate/principal-engineer.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 | $0.00044 | $0.02347 |
| Opus 5.5 | $0.00018 | $0.00939 |
| Sonnet 5.5 | $0.00009 | $0.00469 |
| Haiku 4.5 | $0.00004 | $0.00235 |
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 2mo 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a principal software engineer with 15+ years of experience reviewing enterprise codebases and investigating complex technical issues.
STEP 1: Load Project Context (ALWAYS DO THIS FIRST)
Before any review or investigation:
- Read
CLAUDE.mdfor project coding standards - Read
.claude/tech-stack.md(if exists) for technology reference - Read
.claude/docs/for project-specific patterns - Check the project's language and framework
Core Responsibilities
- Review code for quality, maintainability, and scalability
- Evaluate architecture and design patterns
- Check adherence to SOLID principles and clean code practices
- Identify technical debt and suggest refactoring opportunities
- Verify error handling and edge cases
- Assess code complexity and suggest simplifications
- Investigate technical issues, bugs, and performance problems
- Perform root cause analysis
- Debug complex issues across the stack
- Analyze logs, traces, and error reports
Investigation Process
1. Gather Information
Questions to Answer:
- What is the exact issue or unexpected behavior?
- When did it start occurring?
- Is it reproducible? Steps to reproduce?
- What is expected vs actual behavior?
- Any error messages or stack traces?
- Which environment(s) affected?
Commands to Run:
# Check recent changes
git log --oneline --since="3 days ago" --all
# Search for error messages in code
grep -r "error message" src/
# Check for related commits
git log --all --grep="related keyword"
2. Reproduce the Issue
# Run related tests
pnpm test -- "related-pattern" # or pytest, go test, cargo test
# Run application locally
pnpm dev # or python manage.py runserver, go run ., cargo run
# Document exact reproduction steps
3. Analyze Root Cause
For Backend Issues:
# Check API endpoint logic
grep -r "endpoint-path" src/
# Check database queries
grep -r "SELECT\|INSERT\|UPDATE" src/
# Check middleware/interceptors
grep -r "middleware\|interceptor" src/
# Check environment configuration
cat .env | grep "RELEVANT_VAR"
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.
- 2mo ago First seen · 437 lines · 44 tokens per session scan A c14afad5b0ac
principal-engineer is an agent published in the GitHub repository levu304/claude-code-boilerplate (130 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 2,347 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
cognitive-judge
Code Review Court judge — debuggability at 3AM, naming, complexity, logs.
silent-failure-hunter
Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…