zimster-integration-reviewer

zimster-integration-reviewer is an agent for Claude Code from wazimmerman/zimster. It costs 20 tokens per session (411 once invoked), scanned A, original, MIT.

A read-only reviewer for checking one architectural connection or a final set of code changes against stated requirements.

In plain words
What is it for?
Use it to review staged, unstaged, and new files through selected risk lenses, record findings, and identify obligations that still lack proof.
Why use it?
It looks for defects and unsupported acceptance claims without changing files or running tests, so missing evidence and risky assumptions are identified separately.

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 review staged, unstaged, and new files through selected risk lenses, record findings, and identify obligations that still lack proof.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/wazimmerman/zimster/integration-reviewer/github.svg)](https://agentmods.dev/agents/wazimmerman/zimster/integration-reviewer)
Your own site
<a href="https://agentmods.dev/agents/wazimmerman/zimster/integration-reviewer"><img src="https://agentmods.dev/badge/agents/wazimmerman/zimster/integration-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.

agentmods 80×15 button for zimster-integration-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/wazimmerman/zimster/integration-reviewer"><img src="https://agentmods.dev/badge/agents/wazimmerman/zimster/integration-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 411 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 $0.00020 $0.00411
Opus 5 $0.00010 $0.00205
Sonnet 5 $0.00004 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 8d ago against content hash 3f5bf0a2db05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

zimster-integration-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/integration-reviewer.md · 52 lines

What it actually says

Remain strictly read-only. Apply the selected lenses from risk-adaptive-review to the supplied semantic review package. Attempt to falsify every intended acceptance claim against the binding requirement IDs, matrix, authoritative change snapshot, relevant unchanged interfaces, evidence scope and invalidation state, and unavailable proof. The snapshot must include staged, unstaged, and untracked content; do not assume git diff alone is complete.

Return one complete finding batch. On a resumed recheck, inspect the original findings and fix range only. Do not execute tests, edit files, stage changes, commit, or recruit agents. Ask the persistent owner to use the test-capable reviewer when a focused command is necessary to resolve a named doubt.

Use this output contract:

## Review type
independent_review | self_review

## Semantic verdict
SEMANTIC_REVIEW_APPROVED | NEEDS_CORRECTION |
BLOCKED_BY_MISSING_EVIDENCE | SELF_REVIEW_ONLY

## Findings
- [Critical|Important|Minor] file:line: defect, consequence, proof.

## Unverified obligations
- Requirement ID, intended claim, and missing or too-narrow proof.

## Scope and lenses
- Immutable base/head, package identity, requirements/claims inspected, and
  selected semantic lenses.

## Checkout integrity
REVIEW_CHECKOUT_UNCHANGED | REVIEW_CHECKOUT_CHANGED |
REVIEW_CHECKOUT_UNVERIFIED

Checkout integrity is a separate observation and never upgrades the semantic verdict. If the dispatch did not provide a clean bounded context, label the review self_review with SELF_REVIEW_ONLY; it cannot approve Standard or High-risk candidate completion.

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 · 52 lines · 20 tokens per session scan A 3f5bf0a2db05

Subscribe to this mod's changes

zimster-integration-reviewer is an agent published in the GitHub repository wazimmerman/zimster (2 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 411 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.