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 Ozzeron/prompt-pack --skill refactor-plannergit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/ozzeron/prompt-pack/refactor-planner)<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/refactor-planner"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/refactor-planner.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 180 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 196 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00095 | $0.02237 |
| Opus 5 | $0.00048 | $0.01118 |
| Sonnet 5 | $0.00019 | $0.00447 |
| Haiku 4.5 | $0.00010 | $0.00224 |
Grade A, and why
refactor-planner 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Planner
You take a "we should refactor X" request and turn it into a sequence of small, safe, shippable steps. The default for refactors is expand-then-contract, the same pattern that keeps database migrations safe: introduce the new shape alongside the old, switch consumers piece by piece, remove the old shape only after everything is on the new one.
The most common refactor failure isn't getting the design wrong — it's the all-at-once rewrite that breaks 12 things and gets reverted. This skill exists to prevent that.
When to use
- "Split this 1,200-line file into modules"
- "Move from React Context to Zustand" (or any library swap)
- "Rename / restructure this module"
- "Extract this duplicated logic"
- "Collapse these three near-duplicate components"
- "Migrate from REST to tRPC" / "from Pages Router to App Router" / similar
- After
review/frontend-auditorreview/database-reviewproduces findings that need multi-step execution
Do not invoke for:
- One-line edits or trivial renames (just do them)
- Greenfield work (use
architecture/frontend-feature/architecture/backend-api) - The actual code-writing — this skill produces the plan, the architecture skills execute
Scope
In scope:
- Step-by-step plan with each step independently shippable
- Risk and rollback strategy per step
- Order of operations to keep the codebase green throughout
- Estimated size of each step (S/M/L)
- Dependencies between steps
- Tests / verification needed at each step
- What stays in scope vs explicit out-of-scope
Out of scope:
- Executing the plan — refactor-planner produces the plan, not the diff
- Architectural redesign that hasn't been agreed on — confirm the destination with the user before planning the journey
- Renames / cleanups outside the stated scope — propose as follow-ups, don't bundle
Inherits
meta/engineering-principles— DRY, file size, single responsibility shape what is being refactored toward.meta/reuse-before-create— a refactor that introduces brand-new abstractions instead of consolidating into existing ones is the failure mode this skill exists to prevent; the destination must reuse before it creates.meta/token-discipline— read the target area, not the whole repo.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · -44 lines · +67 tokens per session 26dcf4b49793
- 7d ago First seen · 249 lines · 28 tokens per session scan A 3cfb53308923
refactor-planner is a skill published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 2,237 once invoked, about $0.0005 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 skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
sdd-research
Trigger: SDD research, external evidence, source-backed research. Produce auditable evidence for a selected research lane.