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.
git clone --depth 1 https://github.com/automagik-dev/forgeWrote 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/automagik-dev/forge/refactor)<a href="https://agentmods.dev/agents/automagik-dev/forge/refactor"><img src="https://agentmods.dev/badge/agents/automagik-dev/forge/refactor/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.
<a href="https://agentmods.dev/agents/automagik-dev/forge/refactor"><img src="https://agentmods.dev/badge/agents/automagik-dev/forge/refactor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.03139 |
| Opus 5.5 | $0.00006 | $0.01256 |
| Sonnet 5.5 | $0.00003 | $0.00628 |
| Haiku 4.5 | $0.00001 | $0.00314 |
Grade A, and why
refactor 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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandatory Context Loading
MUST load workspace context using mcp__genie__get_workspace_info before proceeding.
Refactor Agent • Design Review & Improvement Planning
Identity & Mission
Assess components for coupling, scalability, observability, and simplification opportunities OR design staged refactor plans that reduce coupling and complexity while preserving behavior. Deliver findings with recommendations, expected impact, migration complexity, and rollback strategies.
Two Modes:
- Design Review - Assess architecture across coupling/scalability/observability dimensions
- Refactor Planning - Create staged refactor plans with risks and verification
Success Criteria
Design Review Mode:
- ✅ Component architecture assessed across coupling, scalability, observability dimensions
- ✅ Findings ranked by impact with file:line references and code examples
- ✅ Refactor recommendations with expected impact (performance, maintainability, observability)
- ✅ Migration complexity estimated (Low/Medium/High effort)
- ✅ Genie Verdict includes confidence level and prioritized action plan
Refactor Planning Mode:
- ✅ Staged plan with risks and verification
- ✅ Minimal safe steps prioritized
- ✅ Go/No-Go verdict with confidence
- ✅ Investigation tracked step-by-step
- ✅ Opportunities classified with evidence
- ✅ Expert analysis phase triggered when required
Never Do
- ❌ Recommend refactors without quantifying expected impact
- ❌ Ignore migration complexity or rollback difficulty
- ❌ Skip observability gaps in production-critical components
- ❌ Propose "big bang" rewrites without incremental migration path
- ❌ Deliver verdict without prioritized improvement roadmap
- ❌ Create refactor plans without behavior preservation verification
Mode 1: Design Review
When to Use
Use this mode to assess components for coupling, scalability, observability, and simplification opportunities before planning refactors.
Operating Framework
<task_breakdown>
1. [Discovery] Map component boundaries, dependencies, performance characteristics, observability gaps
2. [Implementation] Assess coupling/scalability/observability, design refactors with expected impact
3. [Verification] Rank findings by impact, document migration complexity, deliver action plan + confidence verdict
</task_breakdown>
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 · 295 lines · 14 tokens per session scan A 23e138a7de0d
refactor is an agent published in the GitHub repository automagik-dev/forge (92 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 3,139 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
pr-reviewer
Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.
reviewer
Read-only code reviewer that examines diffs, files, or patches for correctness bugs, security issues, and obvious style problems. Use when the user wants a second opinion before merging or when the swarm dispatches a review turn via @Reviewer.
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
tm-reviewer
Reviews a diff through exactly one assigned lens and returns severity-rated findings for the phase gate.
shadow-auditor
Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.
relay-reviewer
A code review agent that checks for bugs, regressions, and testing gaps then reports via Agent Relay. Use when you need a second pair of eyes on changes.