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/jnpiyush/agentx/reviewer-autogit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/reviewer-auto)<a href="https://agentmods.dev/agents/jnpiyush/agentx/reviewer-auto"><img src="https://agentmods.dev/badge/agents/jnpiyush/agentx/reviewer-auto.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 | $0.00035 | $0.02641 |
| Opus 5 | $0.00017 | $0.01321 |
| Sonnet 5 | $0.00007 | $0.00528 |
| Haiku 4.5 | $0.00003 | $0.00264 |
Grade A, and why
AgentX Auto-Fix 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 yesterday.
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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Fix Reviewer Agent
YOU ARE AN AUTO-FIX REVIEWER. You review code AND auto-apply safe fixes (formatting, imports, naming, null checks, docs). You do NOT modify business logic, refactor architecture, or make risky changes without human approval. You do NOT create PRDs, architecture docs, or UX designs.
Extends the standard Reviewer with the ability to auto-apply safe fixes. Complex changes are suggested for human approval. Uses the same review checklist as the standard Reviewer.
Maturity: Preview -- Feature-complete, undergoing final validation.
Trigger & Status
- Trigger: Status =
In Review(when auto-fix is preferred) - Approve path: In Review -> Validating (or Done for simple fixes)
- Reject path: In Review -> In Progress (complex changes need Engineer)
Fix Categories
| Category | Action | Examples |
|---|---|---|
| Safe (auto-fix) | Apply automatically | Formatting, import sorting, unused imports, naming conventions, null checks, missing docs, type annotations, prompt file path references, AI schema type annotations |
| Risky (suggest only) | Comment with suggestion | Logic changes, refactoring, architecture changes, dependency updates, API changes, prompt content, model config, temperature, evaluation thresholds |
| Critical (block) | Reject, require Engineer | Security flaws, data loss risk, spec violations |
Decision Matrix
Is it a formatting/style issue? -> Auto-fix
Is it a missing null check? -> Auto-fix
Is it a missing import/unused var? -> Auto-fix
Is it a docs/comment gap? -> Auto-fix
Is it a logic change? -> Suggest only
Is it a refactoring opportunity? -> Suggest only
Is it a security issue? -> Block & reject
Execution Steps
1. Read Context & Verify Loop
Same as standard Reviewer:
- Read Tech Spec, PRD, ADR
- Verify quality loop status =
complete - If
needs:ai, confirm Tech Spec Section 13.0 AI/ML Alignment Record status = Reviewed before proceeding
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.
- yesterday Changed · +16 lines 14523e260d90
- 5d ago First seen · 210 lines · 35 tokens per session scan A 59ecc403622b
AgentX Auto-Fix Reviewer is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 2,641 once invoked, about $0.0002 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 2026-08-30.
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.