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 lexler/skill-factory --skill refactoring-teamgit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/refactoring-team)<a href="https://agentmods.dev/skills/lexler/skill-factory/refactoring-team"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/refactoring-team/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/lexler/skill-factory/refactoring-team"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/refactoring-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.00502 |
| Opus 5.5 | $0.00008 | $0.00201 |
| Sonnet 5.5 | $0.00004 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
refactoring-team 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- refactoring-team — 100% identical, 0 lines differ
What it actually says
STARTER_CHARACTER = 💎
Prerequisites
Agent teams must be enabled in settings:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
If not set, offer to add it before proceeding.
Setup
If $ARGUMENTS provided, use as target path. Otherwise ask for:
- Target path (files or folder to refactor)
- Test command to verify changes
Verify the target path exists and tests pass before proceeding.
Launch the Team
Generate a short random ID: head -c 3 /dev/urandom | xxd -p | head -c 3
Use it to name the teammates:
- Worker:
worker-ID(e.g.worker-a3f) - Reviewer:
reviewer-ID(e.g.reviewer-a3f)
Read the spawn prompts:
- Worker: references/worker-prompt.md
- Reviewer: references/reviewer-prompt.md
Before spawning, replace these placeholders in both prompts:
TARGET_PATH→ actual target pathTEST_COMMAND→ actual test commandLENSES_DIR→${CLAUDE_SKILL_DIR}/references/lensesGUIDES_DIR→${CLAUDE_SKILL_DIR}/references/reviewer-guidesWORKER_NAME→ the worker's name (e.g.worker-a3f)REVIEWER_NAME→ the reviewer's name (e.g.reviewer-a3f)
After Launch
Tell the user:
- Shift+Down cycles between worker and reviewer
- For split panes: set
teammateMode: "tmux"in settings
Monitor Progress
When a worker goes idle, read .refactoring-state to check the lens number. If it skipped a value, message the reviewer to go back and complete the skipped lens first.
What ships with it
50 files 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.
- references/guard-idle-worker.sh 393 B runs code
- references/lenses/01-formatting.md 524 B
- references/lenses/02-naming.md 2.0 KB
- references/lenses/03-method-length.md 1.8 KB
- references/lenses/04-abstraction-consistency.md 2.2 KB
- references/lenses/05-primitive-obsession.md 1.6 KB
- references/lenses/06-domain-alignment.md 2.0 KB
- references/lenses/07-patterns.md 878 B
- references/lenses/08-duplication.md 1.9 KB
- references/lenses/09-structural-storytelling.md 1021 B
- references/lenses/10-semantic-clarity.md 1.4 KB
- references/lenses/11-conditionals.md 1.8 KB
- references/lenses/12-magic-values.md 1.0 KB
- references/lenses/13-comments.md 1.2 KB
- references/lenses/14-cohesion.md 2.3 KB
- references/lenses/15-responsibility.md 1.6 KB
- references/lenses/16-coupling.md 1.3 KB
- references/lenses/17-api-interface.md 1.2 KB
- references/lenses/18-mutable-state.md 1.2 KB
- references/lenses/19-error-handling.md 1.9 KB
- references/lenses/20-wrong-abstraction.md 1.4 KB
- references/lenses/21-emergent-design.md 1.3 KB
- references/lenses/22-outside-box.md 751 B
- references/lenses/23-final-review.md 1.4 KB
- references/reviewer-guides/01-formatting.reviewer.md 612 B
- references/reviewer-guides/02-naming.reviewer.md 1.8 KB
- references/reviewer-guides/03-method-length.reviewer.md 1.7 KB
- references/reviewer-guides/04-abstraction-consistency.reviewer.md 1.9 KB
- references/reviewer-guides/05-primitive-obsession.reviewer.md 2.0 KB
- references/reviewer-guides/06-domain-alignment.reviewer.md 2.0 KB
- references/reviewer-guides/07-patterns.reviewer.md 941 B
- references/reviewer-guides/08-duplication.reviewer.md 2.2 KB
- references/reviewer-guides/09-structural-storytelling.reviewer.md 889 B
- references/reviewer-guides/10-semantic-clarity.reviewer.md 1.2 KB
- references/reviewer-guides/11-conditionals.reviewer.md 1.9 KB
- references/reviewer-guides/12-magic-values.reviewer.md 1.0 KB
- references/reviewer-guides/13-comments.reviewer.md 1.1 KB
- references/reviewer-guides/14-cohesion.reviewer.md 2.3 KB
- references/reviewer-guides/15-responsibility.reviewer.md 1.6 KB
- references/reviewer-guides/16-coupling.reviewer.md 1.5 KB
- references/reviewer-guides/17-api-interface.reviewer.md 1.0 KB
- references/reviewer-guides/18-mutable-state.reviewer.md 1.1 KB
- references/reviewer-guides/19-error-handling.reviewer.md 1.9 KB
- references/reviewer-guides/20-wrong-abstraction.reviewer.md 1.6 KB
- references/reviewer-guides/21-emergent-design.reviewer.md 1.4 KB
- references/reviewer-guides/22-outside-box.reviewer.md 796 B
- references/reviewer-guides/23-final-review.reviewer.md 2.5 KB
- references/reviewer-prompt.md 1.8 KB
- references/worker-prompt.md 1.1 KB
- refine-lens-process.md 4.6 KB
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 · 64 lines · 20 tokens per session scan A a1805b0d7d69
refactoring-team is a skill published in the GitHub repository lexler/skill-factory (239 stars, last pushed 16d ago), licensed Apache-2.0. It adds 20 tokens to every session and 502 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…