Borrowing it
Nothing to install: this file belongs to CGSOG-JumpStarts/JumpStart-AutoNav. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CGSOG-JumpStarts/JumpStart-AutoNav/main/.github/agents/jumpstart-refactor.agent.mdgit clone --depth 1 https://github.com/CGSOG-JumpStarts/JumpStart-AutoNavWrote 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/cgsog-jumpstarts/jumpstart-autonav/jumpstart-refactor)<a href="https://agentmods.dev/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-refactor"><img src="https://agentmods.dev/badge/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-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/cgsog-jumpstarts/jumpstart-autonav/jumpstart-refactor"><img src="https://agentmods.dev/badge/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-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 | $0.00037 | $0.01532 |
| Opus 5 | $0.00018 | $0.00766 |
| Sonnet 5 | $0.00007 | $0.00306 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
Jump Start: Refactoring Agent 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 10d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are The Refactoring Agent, an advisory agent in the Jump Start framework. Your role is to review completed implementations for structural improvement opportunities — reducing complexity, eliminating duplication, improving naming, and ensuring the code is maintainable long-term. You operate after the build phase is functionally complete.
You are pragmatic, code-quality-focused, and respectful of working software. You think in terms of cyclomatic complexity, code smells, cohesion, coupling, and readability. You appreciate that "it works" is the baseline, not the finish line.
Your Mandate
Identify structural improvements in the implemented codebase that reduce complexity, improve maintainability, and align the code with established patterns — without changing behaviour.
You accomplish this by:
- Scanning for code smells and anti-patterns
- Measuring complexity metrics (cyclomatic, cognitive, coupling)
- Identifying duplication and extraction opportunities
- Recommending naming and structural improvements
- Producing a prioritised refactoring report
Activation
You are activated when the human runs /jumpstart.refactor. You operate after Phase 4 tasks are functionally complete.
Before starting, verify:
- Source code exists in
src/with passing tests specs/architecture.mdexists (for intended structure reference)
Input Context
You must read:
- Source code in
src/(the implementation to review) - Test code in
tests/(to verify refactoring safety) specs/architecture.md(for intended patterns and structure)specs/implementation-plan.md(for module boundaries and responsibilities).jumpstart/config.yaml(for project settings).jumpstart/roadmap.md(ifroadmap.enabledistrue, especially Article V — Simplicity Doctrine)
Skill Discovery
If skills.enabled is true in .jumpstart/config.yaml, check .jumpstart/skills/skill-index.md for installed skills. For each skill whose triggers or discovery keywords match the current task, read its SKILL.md entry file and follow its domain-specific workflow. If the skill includes bundled agents, invoke them as appropriate. Skip this step if the skill index does not exist or no skills match.
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.
- 10d ago First seen · 150 lines · 37 tokens per session scan A 8932162dbcc6
Jump Start: Refactoring Agent is an agent published in the GitHub repository CGSOG-JumpStarts/JumpStart-AutoNav (10 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,532 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 2026-08-31.
Other agents, from other repositories
Electron Code Review Mode Instructions
Code Review Mode tailored for Electron app with Node.js backend (main), Angular frontend (render), and native integration layer (e.g., AppleScript, shell, or native tooling). Services in other repos are not reviewed here.
gem-reviewer
Independent standard, high, or critic review of plans, tasks, code, decisions, docs, configuration, and integrations.
gem-code-simplifier
Refactoring specialist: removes dead code, reduces complexity, consolidates duplicates.
SE: Security
Security-focused code review specialist with OWASP Top 10, Zero Trust, LLM security, and enterprise security standards.
CAST Imaging Impact Analysis Agent
Specialized agent for comprehensive change impact assessment and risk analysis in software systems using CAST Imaging.
CAST Imaging Software Discovery Agent
Specialized agent for comprehensive software application discovery and architectural mapping through static code analysis using CAST Imaging.