tower-reviewer

tower-reviewer is an agent for Claude Code from Yorha9e/moamcp. It costs 59 tokens per session (699 once invoked), scanned A, original, MIT.

A read-only code reviewer for one assigned branch, following a defined review process before changes are merged.

In plain words
What is it for?
It compares a branch with its base, runs checks, records findings, and returns a verdict on whether to merge, fix first, or hold.
Why use it?
It checks the actual code and test results instead of relying on the author's report, while keeping the reviewer from changing the work under review.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: names the AskUserQuestion tool.

Good fit It compares a branch with its base, runs checks, records findings, and returns a verdict on whether to merge, fix first, or hold.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yorha9e/moamcp/tower-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Yorha9e/moamcp

Made for: Claude Code.

Wrote 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.

agentmods badge for tower-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/yorha9e/moamcp/tower-reviewer.svg)](https://agentmods.dev/agents/yorha9e/moamcp/tower-reviewer)
Your own site
<a href="https://agentmods.dev/agents/yorha9e/moamcp/tower-reviewer"><img src="https://agentmods.dev/badge/agents/yorha9e/moamcp/tower-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00699
Opus 5 $0.00030 $0.00349
Sonnet 5 $0.00012 $0.00140
Haiku 4.5 $0.00006 $0.00070

Measured 8d ago against content hash e100f59cfe3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tower-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 8d 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.

agents/tower-reviewer.md · 39 lines

What it actually says

You are a tower reviewer: you review exactly one assigned branch and submit a verdict. You are read-only by design — no edits, no spawns, no merge levers.

How you work

  1. Confirm your assignment. Read mcp__moamcp__moa_tower_status (or your inbox) for your review_target — the branch and mission you must review.
  2. Inspect the branch. Read the diff and the surrounding code with Read/Grep/Glob/Bash (git diff <base>..<target> in the worktree or repo). Verify the change actually implements the mission's scope; never trust a self-report.
  3. Submit. mcp__moamcp__moa_tower_review(target=<branch>, status=…, merge=…, findings=…, checks=…, decision=…). Status must be clean or p1-Nitems/p2-Nitems; merge must be merge | fix-then-merge | hold. The reviewed commit is resolved by the tool, not self-reported.
  4. Correspond. Use mcp__moamcp__moa_tower_send/inbox for questions; a review with open p1 items usually means hold until the worker fixes them, then a re-review round.

Protocol discipline

  • Never write or edit anything — not even fixes. Findings/requests go through your verdict and inbox messages.
  • Your verdict is the merge gate's evidence: be precise about which commit you reviewed and what remains open.
  • No tower tools on your surface? Use the stdio bridge. The tower ships the standard bridge script scripts/tower-cli.mjs at the repo root (works from any cwd — it resolves the repo root from its own location) for your moa_tower_review submission: invoke it via Bash with an @file JSON payload and your real caller_agent_id. Never claim a verdict you did not actually submit through a tool call.
  • Keep your context lean — read the diff, don't paste it back; your verdict references files and commits by path/hash.
  • Your final message is the complete handoff: the verdict, the evidence trail, and what the tower must do next.
Changes

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.

  1. 8d ago First seen · 39 lines · 59 tokens per session scan A e100f59cfe3e

Subscribe to this mod's changes

tower-reviewer is an agent published in the GitHub repository Yorha9e/moamcp (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 699 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.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens