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 skills/greglas75/zuvo/refactornpx 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.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 | $0.00079 | $0.32821 |
| Opus 5 | $0.00039 | $0.16411 |
| Sonnet 5 | $0.00016 | $0.06564 |
| Haiku 4.5 | $0.00008 | $0.03282 |
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 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 — 1,559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:refactor
A senior architect executing a structured refactoring workflow. Every refactoring follows ETAP stages (Evaluate, Test, Act, Prove) with quality gates at each transition.
Definition of Done (non-negotiable — read before you start)
A refactor is BLOCKED until proven, and the proof is the CONTRACT, not your say-so. The
canonical order is Prove → record in CONTRACT → Gate → Commit (LAST). The commit is the final
action, and an external git hook (refactor-safety-gate, self-installed at Phase 0) enforces
this: a git commit whose staged files intersect this refactor's scope fence is rejected until
the CONTRACT records a completed Prove step. There is no condensed / light / "5-step" path that
skips this — git hooks fire on every harness, so it cannot be narrated past (two ESCAPES exist and are logged, not hidden: ZUVO_ALLOW_ADHOC=1 bypasses the hook entirely, and ZUVO_GATE_TTL_SEC=0 marks any CONTRACT stale so the Prove check is skipped — both are human-attributable env decisions, never something the skill itself sets).
The four SAFETY gates — never skippable, never reducible by "user scope", never "looks small so I skipped it":
- Characterization coverage of every moved unit, green on the PRE-refactor code (before touching it).
- Independent CQ Auditor (blind audit) → record
prove.blind_audit ∉ {skipped,not_run}. - Adversarial review on the final diff → record
prove.adversarial ∉ {skipped,not_run}. - Remediation: in-fence bugs the audit/adversarial surface are FIXED in this run (staged before the gated commit), NOT backlogged. Only out-of-fence / user-declined items defer (each documented).
TELEMETRY (CONTRACT, retro, run-log) is cheap — always do it. BUILD SCOPE (targeted vs full
turbo build) the user MAY narrow, but only by DECLARING it. Skipping a SAFETY gate, or running it
and parking its findings, = the run is BLOCKED(unsafe). Full stop. Everything below is HOW; this is WHAT.
What ships with it
3 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.
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 First seen · 1,559 lines · 79 tokens per session scan A 60d2e7f9b91f
refactor is a skill published in the GitHub repository greglas75/zuvo (6 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 32,821 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
init
Write or refresh the ## Tech debt operations section in CLAUDE.md so a team shares one source of truth for debt-ops disciplines and cached quality commands. Idempotent. Only the managed section changes; other sections are untouched. Invoked explicitly via /debt-ops:init (solo users get the same content from the…
add
Register a deferred decision in the debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you defer…
metrics
Print a debt-ops health summary from the metrics log, covering registration rate, hook feedback action rate, ADR creation, and AI-authored share. Use when the user asks for "debt-ops metrics", "debt health", "registry stats", or invokes /debt-ops:metrics. Read-only, never writes the log.
review
Audit the debt registry, rank survivors by churn × Fowler quadrant, surface a top-N list, then walk paydown on user follow-up. Use when the user asks to review debt, see what to pay down, work through entries, or invokes /debt-ops:review. Stale entries drop with drop A,B,C.
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…