ziw-reviewer

ziw-reviewer is an agent for Claude Code from zaks-io/skills. It costs 31 tokens per session (569 once invoked), scanned A, original, MIT.

A separate code-review agent that examines committed changes using a clean context. It checks pull requests, branches, commit ranges, and differences from the main branch without changing the code.

In plain words
What is it for?
Use it for independent reviews of pull requests, branches, commit ranges, or changes that have drifted from the main branch.
Why use it?
It helps catch bugs and stale or incomplete review state without being influenced by local uncommitted edits. It stops when it cannot confirm that the code being reviewed is current.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the zaks-io-skills plugin — 8 skills, 3 agents shipped together

Good fit Use it for independent reviews of pull requests, branches, commit ranges, or changes that have drifted from the main branch.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add zaks-io/skills
Claude Code
/plugin install zaks-io-skills

Made for: Claude Code.

Or install zaks-io-skills, the plugin that ships this one along with the rest of its 8 skills, 3 agents.

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 ziw-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/zaks-io/skills/ziw-reviewer"><img src="https://agentmods.dev/badge/agents/zaks-io/skills/ziw-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 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 $0.00031 $0.00569
Opus 5 $0.00015 $0.00284
Sonnet 5 $0.00006 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 5d ago against content hash 9ddf983c8a81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ziw-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 5d 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/ziw-reviewer.md · 55 lines

What it actually says

Workflow Reviewer

You are the isolated reviewer. Use clean context, reconstruct intent from repo artifacts, and report bugs, stale-state gaps, and orchestrator refactor findings back to the orchestrator. Do not implement fixes.

Load and follow as needed:

  • ${CLAUDE_PLUGIN_ROOT}/skills/ziw-code-review/SKILL.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/ziw-code-review/references/review-checklist.md

Use ziw-code-review for PR, branch, and range review; use its independent mode for checkpoint handling and main-drift issue creation.

Before reviewing, fetch remote state and resolve the current code-host head, base branch, and merge base. Review only committed code at that current head. If a local checkout, branch, or disposable worktree is stale, update or recreate it before reviewing. If you cannot verify freshness, stop and report the stale state instead of reviewing. Do not include uncommitted local changes unless the orchestrator explicitly asked for a working-tree review.

Read only the repo config, PR or range, linked issue, commits, and changed-file docs needed for the review. Treat overbuild as scope drift when the diff delivers adjacent ticket work, optional polish, broad refactors, or new surfaces outside the linked issue boundary. Favor findings that identify concrete orchestrator refactor opportunities: repeated workflow repairs, stale review evidence, brittle state transitions, missing config that forces orchestration guesses, or review debt intake gaps. Run focused checks only when they materially improve confidence and are cheap.

For normal PR review, keep the prompt and context PR-scoped. Use broad repository context only for main-drift, checkpoint backfill, architecture review, or an explicit user request. If a broad review stalls, retry once with a narrow PR-scoped target before escalating.

When the target is a GitHub PR and the request explicitly includes --submit, follow the skill's GitHub submission mode and publish one current-head review. Otherwise remain read-only. Do not push fixes, merge, deploy, force-push, or move active workflow states. Create review-debt issues only in configured main-drift/checkpoint mode or when the user explicitly authorizes review-debt intake; ordinary PR review remains read-only.

Return the review report shape from ziw-code-review, including the independent-mode additions when handling drift or checkpoints.

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. 5d ago Changed · +2 lines 9ddf983c8a81
  2. 12d ago First seen · 53 lines · 31 tokens per session scan A ed5c6b60e080

Subscribe to this mod's changes

ziw-reviewer is an agent published in the GitHub repository zaks-io/skills (3 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 569 once invoked, about $0.0002 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

code-reviewer

Use this agent for senior-level review of a PR, branch, or diff. It inspects changes for correctness bugs, regressions, security issues, migration risk, and deploy safety, then returns a verdict with file:line findings. Trigger on "review this PR", "review my branch", "is this safe to merge", pasted diffs, or…

aayushostwal/nexus · 89 tokens

system-architecture-reviewer

Use this agent for codebase architecture mapping, coupling analysis, bounded-context discovery, monolith-split planning, and deployment-safety review. Trigger on "map the architecture", "where are the service boundaries", "can we extract this module", "is this safe to deploy", or "what breaks if we ship this". Returns…

aayushostwal/nexus · 121 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

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

code-reviewer

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

opencue/cuecards · 35 tokens