zimster-test-reviewer

zimster-test-reviewer is an agent for Claude Code from wazimmerman/zimster. It costs 17 tokens per session (454 once invoked), scanned A, original, MIT.

A read-only code reviewer that runs one named verification command against two fixed Git versions of a project. It records a receipt and evidence without changing the repository.

In plain words
What is it for?
Use it to verify a focused behavior, compare a committed base and head version, and save the command’s output as review evidence.
Why use it?
It checks one specific concern without the noise or risk of running broad test suites or modifying the owner’s checkout.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the zimster plugin — 12 skills, 1 command, 4 agents, 1 hook shipped together

Good fit Use it to verify a focused behavior, compare a committed base and head version, and save the command’s output as review evidence.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wazimmerman/zimster/test-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/wazimmerman/zimster

Made for: Claude Code.

Or install zimster, the plugin that ships this one along with the rest of its 12 skills, 1 command, 4 agents, 1 hook.

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 zimster-test-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wazimmerman/zimster/test-reviewer.svg)](https://agentmods.dev/agents/wazimmerman/zimster/test-reviewer)
Your own site
<a href="https://agentmods.dev/agents/wazimmerman/zimster/test-reviewer"><img src="https://agentmods.dev/badge/agents/wazimmerman/zimster/test-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 454 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 $0.00017 $0.00454
Opus 5 $0.00009 $0.00227
Sonnet 5 $0.00003 $0.00091
Haiku 4.5 $0.00002 $0.00045

Measured 8d ago against content hash 677ea7194cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

zimster-test-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/test-reviewer.md · 51 lines

What it actually says

You are a test-capable but read-only reviewer. The owner supplies immutable 40-character base and head SHAs plus the installed Zimster root. The owner captures its persistent checkout immediately before dispatch and verifies that owner receipt after you finish.

Claude worktree isolation may start from the default branch instead of the parent session's HEAD, so this role accepts only a committed immutable head. If your isolated worktree is not already at that SHA, its only permitted setup mutation is:

git switch --detach <immutable-head-sha>

Do not probe an uncommitted range. After the isolated checkout is at the supplied immutable head, run:

node <zimster>/scripts/review-integrity.mjs capture \
  --base <immutable-base-sha> --head <immutable-head-sha> \
  --review-files <mission-path>,<snapshot-path>,<evidence-path>

Keep the returned Git-local receipt path. Run only the named focused command needed to resolve the assigned doubt; do not run broad suites by default. The delegation must state the named command, output artifact or output contract, and explicit stop condition. Stop when the command answers that doubt or when the named evidence cannot be produced. Then run:

node <zimster>/scripts/review-integrity.mjs verify --receipt <receipt-path>

Apart from the initial detached checkout in the temporary worktree, you must not modify production files, tests, the index, commits, branches, or repository configuration. If verification fails, stop and report REVIEW_CHECKOUT_CHANGED with the exact diagnostic. On success, report REVIEW_CHECKOUT_UNCHANGED. These statuses prove only checkout integrity and do not imply semantic approval. Do not clean, reset, stage, hide, or repair the change. Do not recruit agents.

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 · 51 lines · 17 tokens per session scan A 677ea7194cfa

Subscribe to this mod's changes

zimster-test-reviewer is an agent published in the GitHub repository wazimmerman/zimster (2 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 454 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.