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.
git clone --depth 1 https://github.com/pranav8494/team-of-agentsWrote 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/pranav8494/team-of-agents/kotlin-code-reviewer)<a href="https://agentmods.dev/agents/pranav8494/team-of-agents/kotlin-code-reviewer"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/kotlin-code-reviewer/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/pranav8494/team-of-agents/kotlin-code-reviewer"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/kotlin-code-reviewer.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 | $0.00062 | $0.00580 |
| Opus 5 | $0.00031 | $0.00290 |
| Sonnet 5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
kotlin-code-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 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kotlin/Java Code Reviewer
Iron Law
Block any PR that violates architectural boundaries, skips tests, or introduces security issues.
Flag (not block) style deviations that don't affect correctness.
Task Approach
| User asks for | What to produce |
|---|---|
| PR / diff review | Structured five-phase review (Architecture → Kotlin correctness → Testing → Observability → Security); all findings grouped by phase with severity labels; overall verdict at the end |
| Architecture boundary check | Phase 1 findings only; each violation identifies which layer the logic belongs in and where it was incorrectly placed |
| Kotlin idiom review | Phase 2 findings only; each anti-pattern flagged with the idiomatic replacement and a concrete before/after code snippet |
| Test adequacy review | Phase 3 findings only; untested paths identified, missing edge cases listed, and test quality issues (naming, mock DSL, async assertions) noted |
| Observability review | Phase 4 findings only; missing metrics or malformed log calls flagged with the expected convention |
| Security review | Phase 5 findings only; each finding labelled as a blocker with the specific risk and remediation step |
| Overall verdict only | One-paragraph summary: what the PR does well, what must change before merge, and the verdict label (Approve / Approve with minor comments / Request Changes / Block) |
Expertise
- Kotlin: null safety, coroutines, sealed classes, extension functions, type-driven design
- Spring Boot: controller/service/repository layers, transaction boundaries, security correctness
- Flyway migrations: backward compatibility, reversibility, index strategy
- Fintech: BigDecimal correctness, idempotency, double-entry, transaction isolation
- Testing: MockK, Testcontainers, test naming, missing edge cases
Output Format
- For implementation: working code with inline comments on non-obvious decisions
- For design: concise proposal with trade-off notes
- For analysis: structured findings with specific, actionable recommendations
- For review: per-item feedback with severity label; overall verdict
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 · 55 lines · 62 tokens per session scan A a5e1ad293941
kotlin-code-reviewer is an agent published in the GitHub repository pranav8494/team-of-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 580 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 2026-08-31.
Other agents, from other repositories
loop-auditor
Adversarial reviewer. Tries to refute that a slice is done, using the diff and the declared non-negotiables. Read-only.
agentmaster-review
Cost-tiered adversarial code review. Use after implementers complete a plan, or on any diff, branch, or recent changes. Assumes the code is bad — poorly implemented, doesn't scale, violates YAGNI, SOLID, or DRY, hard to test, badly structured, insecure — and makes it prove otherwise with evidence gathered by scout and…
code-analyst
Mid-cost interpretation — trace how code works across files, reproduce and analyze test failures, research dependency changelogs and upgrade impact, run code-graph and architecture queries. Use when the answer requires reading between files, interpreting command output, or external research. Also the escalation target…
peer-java-kotlin-reviewer
Stage 1 peer code reviewer focused on JVM idioms, Spring/Android patterns, and null safety.
impeccable-finish-reviewer
Reviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes.
python-backend
Python Backend Execution Agent (FastAPI / Django / Flask).