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 skills add andrewsrigom/agent-skills --skill request-refactor-plangit clone --depth 1 https://github.com/andrewsrigom/agent-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/skills/andrewsrigom/agent-skills/request-refactor-plan)<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/request-refactor-plan"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/request-refactor-plan/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/skills/andrewsrigom/agent-skills/request-refactor-plan"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/request-refactor-plan.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 | $0.00045 | $0.00506 |
| Opus 5.5 | $0.00018 | $0.00202 |
| Sonnet 5.5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
request-refactor-plan 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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Request Refactor Plan
Use this skill when the user wants a refactor plan, not a direct code change.
Scope
- clarifying the real problem behind a refactor request
- evaluating alternative approaches
- defining what is in and out of scope
- checking test coverage expectations
- breaking the work into small safe commits
Default path
- Capture the refactor goal in the user's terms.
- Inspect the relevant code to verify the current state.
- Identify at least one alternative to the proposed direction.
- Clarify scope, boundaries, and non-goals.
- Check what tests already protect the area and what new tests are needed.
- Write the plan as tiny commits that leave the system working at each step.
When to deviate
- Treat the work as a feature plan instead if the request actually changes behavior rather than structure.
- Collapse alternatives only when one direction is already strongly constrained by the codebase or product requirements.
- Escalate to architecture review if the refactor request is really about a larger boundary problem than one plan can safely cover.
Guardrails
- Do not confuse a refactor with a feature request.
- Keep the plan durable: avoid coupling it to exact file paths unless necessary.
- Make each step small enough to review and revert safely.
- If test coverage is missing, say so explicitly in the plan.
Avoid
- treating a behavior change like a pure refactor
- writing one giant “do everything” refactor step
- tying the plan too tightly to file paths when the boundary can be described conceptually
- hand-waving missing tests
Verification checklist
- the problem statement distinguishes refactor from feature work
- at least one alternative was considered
- scope and non-goals are explicit
- each step is small enough to review and revert
- testing coverage and gaps are called out clearly
Output Shape
When answering with this skill, prefer:
- problem statement
- recommended direction
- alternatives considered
- commit-by-commit plan
- testing decisions
- out-of-scope section
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.
- 2mo ago First seen · 69 lines · 45 tokens per session scan A 931e4dd27e3a
request-refactor-plan is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 506 once invoked, about $0.0002 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 2026-08-31.
request-refactor-plan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| request-refactor-planandrewsrigom/agent-skills | Skill | 2 | 7mo ago | MIT | A | 45 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |