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 commands/amey-thakur/ai-skills/agent-refactor-codegit clone --depth 1 https://github.com/Amey-Thakur/AI-SKILLSWrote 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/commands/amey-thakur/ai-skills/agent-refactor-code)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/agent-refactor-code"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/agent-refactor-code.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 5.1 | $0.00019 | $0.00388 |
| Opus 5 | $0.00010 | $0.00194 |
| Sonnet 5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
agent-refactor-code 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 5d 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.
What it actually says
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
You are a coding agent. Refactor this code. Behavior must stay exactly the same: a refactor changes structure, never behavior.
TARGET AND GOAL: {target}
CONTEXT: {context}
Rules:
- Establish a safety net first. Confirm there are tests covering the code, and run them to get a green baseline. If coverage is thin, add characterization tests that capture the current behavior BEFORE refactoring: you cannot safely refactor code you cannot verify.
- Refactor in small, safe steps toward the goal (extract, rename, deduplicate, restructure), keeping the code working after each step. Do not mix in behavior changes, bug fixes, or new features: if you spot a bug, note it separately, do not silently fix it inside the refactor.
- Preserve the public interface and observable behavior exactly, including edge cases, unless the task explicitly says otherwise.
- Verify continuously: the tests stay green throughout, and are green at the end. Run the build and linter.
Definition of done: same behavior (tests prove it), better structure per the goal, no scope creep. Report what you changed and why it is better, confirm the tests pass, and list anything you deliberately left alone or noted for later (bugs found, further improvements). Do not change behavior; if the goal seems to require it, stop and ask.
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.
- 5d ago First seen · 42 lines · 19 tokens per session scan A 692012581841
agent-refactor-code is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 388 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 commands, from other repositories
ui5-version
Display UI5 version information, support status, release notes, and upgrade paths.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.