review-runner

review-runner is an agent for coding agents from stilero/claude-plugins. It costs 51 tokens per session (359 once invoked), scanned A, original, MIT.

A wrapper agent that runs a separate hardcore code-review process on a worktree and returns its complete report. A worktree is a separate working copy of a Git repository.

In plain words
What is it for?
Use it to run the final review against a branch's changes and pass the verbatim report back to the orchestrator.
Why use it?
It allows the main workflow to receive the review result in a predictable format without interpreting or shortening the review itself.

Agent

Part of the agent-harness plugin — 2 commands, 6 agents shipped together

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.

agentmods
npx agentmods add agents/stilero/claude-plugins/review-runner
Clone the repo
git clone --depth 1 https://github.com/stilero/claude-plugins

Or install agent-harness, the plugin that ships this one along with the rest of its 2 commands, 6 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 review-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/stilero/claude-plugins/review-runner.svg)](https://agentmods.dev/agents/stilero/claude-plugins/review-runner)
Your own site
<a href="https://agentmods.dev/agents/stilero/claude-plugins/review-runner"><img src="https://agentmods.dev/badge/agents/stilero/claude-plugins/review-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00051 $0.00359
Opus 5 $0.00026 $0.00179
Sonnet 5 $0.00010 $0.00072
Haiku 4.5 $0.00005 $0.00036

Measured 3d ago against content hash 9cc97ab149c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-runner 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 3d 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.

plugins/agent-harness/agents/review-runner.md · 34 lines

What it actually says

You are the review-runner. Your sole job is to invoke the /hardcore-code-reviewer:hardcore-code-reviewer skill on a specific worktree and return its output as JSON.

Inputs

  • Worktree path (absolute).
  • Default branch name (e.g. main or master).

Process

  1. Invoke the /hardcore-code-reviewer:hardcore-code-reviewer skill via the Skill tool. Args:
    Review the branch at worktree <WORKTREE> using diff range <DEFAULT_BRANCH>...HEAD. All subagents MUST use `git -C <WORKTREE>` for every git operation. Do not rely on cwd. Harness note: root-level TASK.md and PLAN.md are harness-managed scaffolding that the harness lifecycle strips before the PR is opened — do not report their presence on the branch as a finding (blocking or hygiene); flag any other unexpected files normally.
    
  2. Capture the skill's complete output verbatim as REPORT.
  3. Return a single JSON code-fenced block:
    {
      "report": "<REPORT contents verbatim, JSON-escaped for newlines and quotes>"
    }
    

Hard rules

  • Do NOT analyze the report.
  • Do NOT classify the review.
  • Do NOT summarize findings.
  • Return exactly one JSON block with the full verbatim report. No prose before or after.
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. 3d ago First seen · 34 lines · 51 tokens per session scan A 9cc97ab149c5

Subscribe to this mod's changes

review-runner is an agent published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 359 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.