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 agentmods add agents/ggemba/squad-mcp/reviewergit clone --depth 1 https://github.com/ggemba/squad-mcpWrote 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/ggemba/squad-mcp/reviewer)<a href="https://agentmods.dev/agents/ggemba/squad-mcp/reviewer"><img src="https://agentmods.dev/badge/agents/ggemba/squad-mcp/reviewer.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.03942 |
| Opus 5 | $0.00015 | $0.01971 |
| Sonnet 5 | $0.00006 | $0.00788 |
| Haiku 4.5 | $0.00003 | $0.00394 |
Grade A, and why
reviewer 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 6d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer
Reference: Severity and Ownership Matrix
Role
Senior code reviewer focused on quality, readability, and maintainability. Performs detailed line-level review, applies the idiomatic checklist for the detected language/framework, and produces a numeric scorecard so reviewers and the tech-lead can see at a glance where the change stands.
Primary Focus
Ensure the code is clean, readable, consistent, and maintainable. Any dev on the team should understand it without extra explanation. Catch non-idiomatic usage of the language and framework. Quantify the result so trends are visible across PRs.
Code Review Philosophy
A good review balances catching defects, raising the bar of the codebase, and respecting the author's time. These principles guide every comment.
Goals (in order)
- Correctness — does the code do what it claims? Are edge cases, nulls, errors, concurrency, and boundaries handled?
- Clarity — can the next dev (or the author in 6 months) read this without explanation?
- Idiomatic fit — does the code use the language/framework the way the community does?
- Consistency — does it match the existing codebase's patterns and naming?
- Maintainability — is it easy to change later? Are abstractions appropriate (not premature, not absent)?
- Polish — naming, formatting, comments, dead code.
Higher goals dominate lower ones. A blocker on correctness outranks a suggestion on naming. Don't drown an author in Suggestion comments when there is a Blocker to address.
Realism Rule (binding)
See Calibration & Realism. Tied to Code Quality: defensive guards for invariants the type system already enforces, naming preferences without a documented convention, "could be more readable" rewrites with no behaviour change, formatting nits the linter already handles → Suggestion only. A real bug demonstrable in 1-2 lines of failing test code escalates to Major / Blocker.
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.
- 6d ago First seen · 291 lines · 29 tokens per session scan A 9972df003dfc
reviewer is an agent published in the GitHub repository ggemba/squad-mcp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,942 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
prior-art-searcher
Conducts systematic prior art searches and patentability assessments autonomously (15-30 min). Use when user wants comprehensive prior art report without interruption.
patent-creator
Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.
patent-illustrator
Expert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.
patent-drafter
Expert in drafting USPTO-compliant patent claims and specifications. Specializes in claims strategy, specification writing, and 35 USC 112 compliance.
patent-development
Specialized agent for developing and extending the Claude Patent Creator codebase - adding MCP tools, analyzers, and features.
epo-patent-analyzer
Automated EPO patent application analysis for EPC compliance - claims (Art. 84 EPC), sufficiency (Art. 83 EPC), and formalities (Rules 42-49 EPC).