implementation-reviewer

implementation-reviewer is an agent for Claude Code from vsladkov/claudex-stereo. It costs 19 tokens per session (386 once invoked), scanned A, original, Apache-2.0.

A read-only reviewer that checks the changes made by a `/stereo:implement` run and returns a machine-readable acceptance decision.

In plain words
What is it for?
Use it to inspect the baseline and current worktree, run only named tests or static checks, and return JSON stating whether the implementation is acceptable.
Why use it?
It gives the implementation process a consistent way to decide whether the changes are acceptable and records any required fixes.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. 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 stereo plugin — 4 skills, 15 commands, 7 agents, 3 hooks shipped together

Good fit Use it to inspect the baseline and current worktree, run only named tests or static checks, and return JSON stating whether the implementation is acceptable.

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 vsladkov/claudex-stereo
Claude Code
/plugin install stereo

Made for: Claude Code.

Or install stereo, the plugin that ships this one along with the rest of its 4 skills, 15 commands, 7 agents, 3 hooks.

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 implementation-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vsladkov/claudex-stereo/implementation-reviewer.svg)](https://agentmods.dev/agents/vsladkov/claudex-stereo/implementation-reviewer)
Your own site
<a href="https://agentmods.dev/agents/vsladkov/claudex-stereo/implementation-reviewer"><img src="https://agentmods.dev/badge/agents/vsladkov/claudex-stereo/implementation-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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 5.1 $0.00019 $0.00386
Opus 5 $0.00010 $0.00193
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 6d ago against content hash 66ab6dd461e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

implementation-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 6d 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/stereo/agents/implementation-reviewer.md · 44 lines

What it actually says

You are the Claude-side implementation reviewer for /stereo:implement. The main Claude session orchestrates the loop; you inspect one implementation delta and return one verdict. The command invokes you in the foreground with run_in_background: false and validates your result before acting. The invoking command supplies the complete filled implementation-review brief in the prompt.

Operating rules:

  • Never edit files, commit, push, or delegate work.
  • Use Read, Glob, Grep, and read-only git commands to inspect the baseline and current worktree.
  • Run only the repository test/static-check commands the orchestrator's prompt explicitly names.
  • Do not ask the user questions.

The canonical output contract is ${CLAUDE_PLUGIN_ROOT}/schemas/implementation-review-output.schema.json. Return only one raw JSON object, with no Markdown fence or prose, using this shape:

{
  "acceptable": true,
  "summary": "non-empty string",
  "fixes": [
    {
      "file": "repository-relative path",
      "line": 1,
      "problem": "what is wrong",
      "correct": "what correct behavior looks like"
    }
  ]
}

acceptable must be a boolean, summary a non-empty string, and fixes an array. Every fix must contain a non-empty file, a positive integer line, a non-empty problem, and a non-empty correct. When acceptable is true, fixes must be empty. When material defects remain, acceptable must be false and fixes must be non-empty.

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. 6d ago First seen · 44 lines · 19 tokens per session scan A 66ab6dd461e0

Subscribe to this mod's changes

implementation-reviewer is an agent published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed 28d ago), licensed Apache-2.0. It adds 19 tokens to every session and 386 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.

Related

Other agents, from other repositories

cross-cli-consistency-checker

Audit all cli-web- CLIs for convention drift against skills/shared/CONVENTIONS.md, including replskin drift via cli-web-devkit drift and .manifest.json presence. Reports PASS/FAIL per check per CLI in a matrix format. Use periodically or before releases to catch inconsistencies across the CLI portfolio.

ItamarZand88/CLI-Anything-WEB · 71 tokens

traffic-fidelity-reviewer

Review a cli-web- CLI implementation against its APP.md API map. Checks endpoint coverage, parameter fidelity, response parsing accuracy, dead client methods, and stale API map entries. Returns scored findings. Use during Phase 4 standards review — dispatched by the standards skill.

ItamarZand88/CLI-Anything-WEB · 59 tokens

harness-compliance-reviewer

Review a cli-web- CLI for convention compliance against skills/shared/CONVENTIONS.md. Checks exception hierarchy, auth patterns, client architecture, CLI patterns (UTF-8, shlex, handleerrors), and the JSON envelope STRUCTURE in code (runtime output validity belongs to output-ux-reviewer). Returns scored findings. Use…

ItamarZand88/CLI-Anything-WEB · 80 tokens

skeptic

Adversarial verifier for a single review finding. Given one claimed issue plus the code, tries to refute it against reality to cut false positives. Use to verify findings before they are reported. Read-only. Also cross-checks a single research claim against its cited web sources and sibling claims (structural…

restarter/lets-workflow · 72 tokens

actor

Meta-agent that adopts external personalities and adapts them to LETS modes. Loads identity from personality text provided in prompt, then operates as that persona with LETS structured output.

restarter/lets-workflow · 37 tokens

architect

System design expert for architecture reviews, pattern analysis, SOLID principles evaluation, and coupling/abstraction assessments. Use when reviewing structural changes, evaluating design decisions, or analyzing system architecture.

restarter/lets-workflow · 39 tokens