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.
npx agentmods add agents/luisfelipemoro/harness-devkit/reviewergit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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.
[](https://agentmods.dev/agents/luisfelipemoro/harness-devkit/reviewer)<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>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 | $0.00017 | $0.02597 |
| Opus 5 | $0.00009 | $0.01299 |
| Sonnet 5 | $0.00003 | $0.00519 |
| Haiku 4.5 | $0.00002 | $0.00260 |
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.
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 |
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.
- 3d ago First seen · 143 lines · 17 tokens per session scan A 0d7cea9041ad
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.