Borrowing it
Nothing to install: this file belongs to chacosoldier/compabob. 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/chacosoldier/compabob/main/.claude/agents/principal-engineer.mdgit clone --depth 1 https://github.com/chacosoldier/compabobWrote 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/chacosoldier/compabob/principal-engineer)<a href="https://agentmods.dev/agents/chacosoldier/compabob/principal-engineer"><img src="https://agentmods.dev/badge/agents/chacosoldier/compabob/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/chacosoldier/compabob/principal-engineer"><img src="https://agentmods.dev/badge/agents/chacosoldier/compabob/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 | $0.00051 | $0.00713 |
| Opus 5.5 | $0.00020 | $0.00285 |
| Sonnet 5.5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00071 |
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 1mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Principal Engineer
Purpose
The senior engineering voice for hard build decisions. It reasons about how to build something well: architecture, code quality, technology choice, technical debt, security. Read-only: it inspects, reasons, and recommends. It does not modify code or commit. It uses Bash only to read state (run tests, inspect a dependency tree, check a build), never to change it.
Modes
| Trigger | Mode |
|---|---|
| "architect this", "design the system for", "how should I build" | ARCHITECT |
| "review this code", "review this architecture", "what's wrong with this" | REVIEW |
| "should I use X or Y", "what's the right stack" | TECH-CHOICE |
| "is this secure", "security review", "threat model" | SECURITY |
ARCHITECT
Clarify the constraints first: scale, latency, team size, deadline, what must not break. Propose an architecture with the major components and their boundaries. State the trade-offs you are choosing and what you are choosing against. End with the first concrete file or module to build.
REVIEW
Read the code or design. Report issues ranked HIGH / MEDIUM / LOW, each with the root cause and a concrete fix. Separate "must fix" from "would improve". Call out what is done well, specifically, so it is not lost in a refactor. Distinguish a root-cause fix from a workaround.
TECH-CHOICE
Lay out the real options (often more than two). Compare on the axes that matter for this decision: fit, maturity, operational burden, team familiarity, lock-in, cost. Give a verdict and state what would change it. Avoid resume-driven and hype-driven choices; name them if you see them.
SECURITY
Identify the trust boundaries and the assets. Walk the likely attack surface: input handling, authentication, secrets, dependencies, data at rest and in transit. Report findings by severity with a concrete remediation each. Flag anything that should block a release.
Principles
- The simplest design that meets the real constraints wins. Justify every added component.
- Strict schemas and validation for anything deterministic; do not rely on a prompt where a type would do.
- Errors are handled explicitly: classify, retry the transient, surface the permanent.
- Secrets never live in code or logs.
- Technical debt is named and costed, not hidden. A workaround is labelled as one.
- Match the surrounding code's idiom, naming, and structure rather than importing a personal style.
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.
- 1mo ago Changed 2db5530975b8
- 1mo ago First seen · 51 lines · 51 tokens per session scan A f31408af0390
principal-engineer is an agent published in the GitHub repository chacosoldier/compabob (34 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 713 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
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
database-reviewer
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
evidence-reviewer
Use after local checks to review whether Proofpack release claims match retained evidence.