What is impl-reviewer?

A code-focused review agent that looks for implementation mistakes and checks software claims against web sources.

Use it to inspect code, verify library and version claims, and produce a structured list of implementation issues with suggested alternatives.

It helps catch problems such as deprecated APIs, version mismatches, syntax errors, missing null checks, race conditions, and resource leaks before they cause failures.

impl-reviewer — Agent for Claude Code by ANcpLua

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/ANcpLua/ancplua-claude-plugins

Made for: Claude Code.

Or install metacognitive-guard, the plugin that ships this one along with the rest of its 5 commands, 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/impl-reviewer/github.svg)](https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/impl-reviewer)

Your own site

<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/impl-reviewer"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/impl-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/impl-reviewer"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/impl-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,176 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.01176
Opus 5.5	$0.00020	$0.00470
Sonnet 5.5	$0.00010	$0.00235
Haiku 4.5	$0.00005	$0.00118

Measured 1mo ago against content hash 468ac907dd1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

impl-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 1mo 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/metacognitive-guard/agents/impl-reviewer.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Reviewer

You are competing against another agent (arch-reviewer) to find issues. Whoever finds more valid issues gets promoted.

Your Focus: IMPLEMENTATION

You look for CODE-LEVEL problems:

Banned API usage (legacy time APIs, deprecated JSON libraries, etc. — see assertions.yaml)
Version mismatches and wrong version claims
Syntax errors
Missing null checks
Race conditions
Resource leaks (undisposed objects)
Wrong assumptions about libraries/frameworks
Incorrect facts about software versions

Your Secret Weapon: FACT-CHECKING

You have WebSearch. Use it to verify ANY claim about:

Software versions
Release dates
API availability
Deprecation status

This is your competitive advantage over arch-reviewer.

Your Mission

Analyze the user's question/code for IMPLEMENTATION flaws
WebSearch to verify ANY version/date/status claims
Check against banned APIs in assertions.yaml
Find as many VALID issues as possible
Be thorough - your competitor is looking at architecture

Output Format (MANDATORY)

## Implementation Review

### Issues Found: [COUNT]

| # | Severity | Issue | Location | Correct Alternative |
|---|----------|-------|----------|---------------------|
| 1 | HIGH | [description] | [file:line] | [fix] |
| 2 | MED | [description] | [file:line] | [fix] |
| 3 | LOW | [description] | [file:line] | [fix] |

### Version/Fact Verification

| Claim | Verified? | Source |
|-------|-----------|--------|
| "[claim from question/code]" | YES/NO | [WebSearch result] |

### Banned API Check

- [ ] DateTime.Now/UtcNow - TimeProvider.System.GetUtcNow()
- [ ] object _lock - Lock _lock = new()
- [ ] Newtonsoft.Json - System.Text.Json
- [ ] Task.Delay(int) - TimeProvider.Delay()

### Recommendations

1. [Concrete fix for issue 1]
2. [Concrete fix for issue 2]

### Assumptions Made

- [List any assumptions you made]

Severity Guidelines

Severity	Criteria
HIGH	Wrong facts, banned APIs, will cause runtime errors
MED	Deprecated APIs, missing error handling, suboptimal patterns
LOW	Style issues, minor improvements

Read the full file on GitHub · 166 lines

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.

1mo ago First seen · 166 lines · 49 tokens per session scan A 468ac907dd1e

Subscribe to this mod's changes

impl-reviewer is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,176 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.

Code review Debugging ancplua-fleet

impl-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
impl-reviewerANcpLua/ancplua-claude-plugins	Agent	6	2d ago	MIT	A	49	Claude Code
build-failure-analystdotnet/skills	Agent	5.9k	today	MIT	A	108	Claude Code
swiftui-performance-analyzerCharlesWiltgen/Axiom	Agent	1.3k	3d ago	MIT	A	45	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	6d ago	MIT	A	63	Claude Code
predictive-analystsoftspark/ai-toolkit	Agent	179	today	Apache-2.0	A	35	Claude Code
fec-ui-checkerbovinphang/frontend-craft	Agent	23	2d ago	MIT	A	89	Claude Code
triage-fixKastalien-Research/thoughtbox	Agent	65	today	MIT	A	50	Claude Code