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 greglas75/zuvo --skill refactorgit clone --depth 1 https://github.com/greglas75/zuvoWrote 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/greglas75/zuvo/refactor)<a href="https://agentmods.dev/skills/greglas75/zuvo/refactor"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/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/skills/greglas75/zuvo/refactor"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 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 Rogue Agent · line 493 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 540 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 559 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 690 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 758 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 861 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 Rogue Agent · line 1114 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 1290 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- low Excessive Agency · line 848 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00047 | $0.01362 |
| Opus 5.5 | $0.00019 | $0.00545 |
| Sonnet 5.5 | $0.00009 | $0.00272 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
refactor 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:refactor
Refactor the requested symbols while preserving their observed behavior. Resolve
../../shared/includes/execution-policy.md and ../../shared/includes/evidence-reuse.md once.
Follow the user's current authorization, project verification rules and behavior scope.
Argument Parsing
| Argument | Action |
|---|---|
<file(s)> |
Analyze and refactor this scope |
continue |
Resume the selected contract at its recorded phase |
batch <file> |
Load batch handling in references/completion.md and ../../shared/includes/refactor-reference.md |
no-commit |
Finish verification; retain uncommitted work and report its location |
| Other documented flags | Resolve the full argument table in references/bootstrap.md |
Mandatory File Loading
Load only the current phase reference below. Read its required includes when that phase needs
them; use the realpath/hash/context-generation receipt protocol in evidence-reuse.md. After
compaction reload current requirements; a persistent file ledger is not retained context.
Do not concatenate every phase at entry. Missing optional enrichment is a named degradation;
missing mandatory safety definitions blocks the dependent assessment.
Phase routing
| Phase / contract boundary | Read on entry | Required outcome |
|---|---|---|
| 0: discovery | references/bootstrap.md |
Current worktree, capabilities, gate install, scope and refactor type |
| 1: plan | references/planning.md |
Callers, duplication, CQ baseline, behavior/symbol scope and contract |
| 2: characterize | references/characterization.md |
Every moved unit exercised on pre-change code; use ../../shared/includes/regression-fence.md |
| 3: transform | references/transformation.md |
Planned move, targeted verification, independent CQ audit under policy |
| 3: review | references/review.md |
Actual adversarial review of formatted final inputs; finding dispositions |
| 3.5–3.6: fix/audit | references/remediation.md |
Authorized fixes with linked red/green runs; test-quality substage with parent evidence; mutation substage over the tests this run produced |
| 4: completion | references/completion.md |
Shared verifier, content-keyed proof, required telemetry and concise result |
What ships with it
11 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.
- agents/cq-auditor.md 13 KB
- agents/dependency-mapper.md 4.9 KB
- agents/existing-code-scanner.md 5.2 KB
- references/bootstrap.md 12 KB
- references/change-assessment.md 4.4 KB
- references/characterization.md 8.4 KB
- references/completion.md 28 KB
- references/planning.md 20 KB
- references/remediation.md 24 KB
- references/review.md 24 KB
- references/transformation.md 16 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 Changed 45f24ad8bdcf
- 1mo ago Changed · -1,441 lines · -32 tokens per session 8083e0888233
- 1mo ago First seen · 1,559 lines · 79 tokens per session scan A 60d2e7f9b91f
refactor is a skill published in the GitHub repository greglas75/zuvo (7 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,362 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 2026-09-03.
Other skills, from other repositories
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.
ring:creating-worktrees
Creating an isolated git worktree for parallel branch work: selects the directory by priority order, verifies/adds .gitignore safety, auto-installs the detected toolchain's dependencies, runs a baseline test, and reports readiness. Use before a feature that needs isolation from the main workspace or before executing…
changelog
Add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
ai-agent-bench
Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
create-test
Define or implement regression proof: test strategy, black-box or integration tests, KPIs, thresholds, audits, or missing tests.
eval-regression
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.