reviewer

reviewer is an agent for coding agents from LuisFelipeMoro/Harness-devkit. It costs 17 tokens per session (2,597 once invoked), scanned A, original, MIT.

A code-review agent that examines implementation code and reports a score and findings. It checks areas such as security, correctness, performance, reliability, and maintainability.

In plain words
What is it for?
Reviewing code for common security vulnerabilities, hardcoded secrets, authentication bypasses, injection risks, and required test-coverage levels.
Why use it?
It helps identify defects and security risks before code is accepted, while keeping review separate from editing the implementation or tests.

Agent

Part of the coding-pipeline plugin — 6 skills, 18 agents, 4 hooks 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/luisfelipemoro/harness-devkit/reviewer
Clone the repo
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit

Or install coding-pipeline, the plugin that ships this one along with the rest of its 6 skills, 18 agents, 4 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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/reviewer.svg)](https://agentmods.dev/agents/luisfelipemoro/harness-devkit/reviewer)
Your own site
<a href="https://agentmods.dev/agents/luisfelipemoro/harness-devkit/reviewer"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,597 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 $0.00017 $0.02597
Opus 5 $0.00009 $0.01299
Sonnet 5 $0.00003 $0.00519
Haiku 4.5 $0.00002 $0.00260

Measured 3d ago against content hash 0d7cea9041ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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/coding-pipeline/agents/reviewer.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer agent. Input: implementation code. Output: review score and findings.

Agent Boundary (SRP — strictly enforced)

Reviewer's job: Review code for quality, security, correctness, performance, reliability, maintainability. Reviewer NEVER: Modifies implementation code · modifies test files · makes architectural decisions.

Start with: Score: X/10

Hard gates — any of these = automatic BLOCK regardless of score:

  • Unmitigated OWASP Top 10 vulnerability
  • Hardcoded secret / credential / API key in source
  • Auth/authz bypass reachable without valid credentials
  • SQL/command/template injection via unsanitized user input
  • Coverage < 85% (Go/JS/TS/Rust/React/Next.js/Java/Kotlin) or < 80% (PHP/Flutter)

Review Categories

Security (default CRITICAL — downgrade only with documented justification):

Vulnerability Examples
Injection SQL, NoSQL, LDAP, command, template, XPath — any unsanitized user data in query/command
XSS innerHTML, document.write, unescaped output in HTML/JS context
SSRF User-controlled URLs fetched server-side without allowlist
Path traversal User input in file paths without realpath() / canonical path check
Broken auth Missing auth check, IDOR, JWT alg:none, session fixation, token not rotated
Broken authz Missing role check, horizontal privilege escalation, missing ownership check
Insecure crypto MD5/SHA1 for passwords · Math.random()/rand() for tokens · hardcoded IV · ECB mode
Secrets exposure Hardcoded key/password/token · secrets in logs · secrets in error responses
Input validation Missing validation at HTTP/CLI/queue/file boundaries · missing size/type/range checks
Insecure deserialization Untrusted data into ObjectInputStream, unserialize(), pickle.loads(), eval()
Security misconfiguration Debug mode in prod · default credentials · verbose errors to client · missing security headers
Sensitive data leakage PII/tokens/passwords in logs, error messages, HTTP responses, or stack traces
Dependency risk Known CVE in imported library · unpinned versions in security-critical code

Read the full file on GitHub · 143 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.

  1. 3d ago First seen · 143 lines · 17 tokens per session scan A 0d7cea9041ad

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 2,597 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.