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 FarzamMohammadi/the-engineer --skill expert-panel-reviewgit clone --depth 1 https://github.com/FarzamMohammadi/the-engineerWrote 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/farzammohammadi/the-engineer/expert-panel-review)<a href="https://agentmods.dev/skills/farzammohammadi/the-engineer/expert-panel-review"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/expert-panel-review/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/farzammohammadi/the-engineer/expert-panel-review"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/expert-panel-review.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 | $0.00181 | $0.04487 |
| Opus 5 | $0.00090 | $0.02243 |
| Sonnet 5 | $0.00036 | $0.00897 |
| Haiku 4.5 | $0.00018 | $0.00449 |
Grade A, and why
expert-panel-review 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 12d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Panel Review
Run code, architecture, systems, files, or proposed changes through a panel of world-class engineering minds. Each panelist reads the actual source code before rendering judgment. Findings are synthesized into convergence points — where all experts agree, that's where you act first.
Why This Matters
A single perspective — no matter how skilled — has blind spots. Linus sees data structure problems but might over-simplify. Hipp catches testing gaps but might not see the UX impact. Pike spots unnecessary abstraction but might miss domain-specific justifications. The value is in the convergence: when five independent minds, each with different values and priorities, all point at the same problem, that problem is real.
The Panel
Five default perspectives. Each covers a strategic angle that the others miss. The two persona-based panelists (The Engineer, Technical Architect) are powered by full persona files — not summaries. The subagent prompt must include the COMPLETE persona text so the panelist truly embodies it.
1. Linus Torvalds
The creator of Linux and Git. Not his personality — his THINKING about software.
Core philosophy (include verbatim in subagent prompt):
- "Bad programmers worry about the code. Good programmers worry about data structures and their relationships."
- "Complexity is the enemy of reliability."
- "The best code is no code at all."
- "I'm not a visionary, I'm an engineer. I'm looking at the ground and saying 'I'd like to fix this pothole.'"
- Get the data structures right and the code writes itself.
- Don't over-abstract — abstraction should make things clearer, not more complex.
- Performance matters, but correctness matters more.
- The interface IS the design — get the API right.
- Code should be readable by a maintainer who isn't you, years from now.
- Delete code aggressively — every line is a liability.
- Don't design for hypothetical futures — solve the problem you have.
What he catches that others miss: Wrong data models that infect everything downstream. Abstractions that cost more than they save. Clever code that should be clear. Over-segmented file structures.
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.
- 12d ago First seen · 346 lines · 181 tokens per session scan A 921ff3878d32
expert-panel-review is a skill published in the GitHub repository FarzamMohammadi/the-engineer (12 stars, last pushed 2mo ago), licensed MIT. It adds 181 tokens to every session and 4,487 once invoked, about $0.0009 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.
Other skills, from other repositories
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
review-code
Review a code change well — engine-agnostic critical review discipline for an inline dev loop. Defines what to look for (design→correctness→complexity→tests→naming→security), a severity taxonomy, and a review→fix→re-review loop with a hard stop. Use on "review this code", "review my diff", "is this change good"…
code-review
AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security). Also drives the development inner loop: review uncommitted work, fix, re-review before commit.
code-quality
Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.
goga-review-plan
Verify execution plan completeness and correctness.