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 refactor-radargit 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-radar)<a href="https://agentmods.dev/skills/greglas75/zuvo/refactor-radar"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/refactor-radar/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-radar"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/refactor-radar.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 | $0.00071 | $0.04531 |
| Opus 5 | $0.00036 | $0.02266 |
| Sonnet 5 | $0.00014 | $0.00906 |
| Haiku 4.5 | $0.00007 | $0.00453 |
Grade A, and why
refactor-radar 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 4d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:refactor-radar
Decide WHAT is worth changing before zuvo:refactor decides HOW. Start with deterministic
discovery, validate the evidence, then propose bounded work. Never turn a ranked row into
an authorized refactor automatically.
Modes and boundaries
- DISCOVER (default): read code, metadata and existing decisions; save the raw results
and the ranked report, then link them in the answer. Saving these requested deliverables
needs no extra approval and is not REGISTER. No product edits, queue, ledger, history,
reservation, dependency install, commit or PR. An authorized farm run may stage a private,
disposable
--prepare-farmjob; disclose its location. Explicit chat-only/no-file-write requests (--no-save) and--dry-runsuppress report files; do not ask users to opt in. - REGISTER: only when asked to save approved work; validate G1–G5, write a new queue and, if requested, append decisions/history. This does not reserve files or start work.
- EXECUTE: a separate request routed to
zuvo:refactororzuvo:write-tests. Recheck SHA, reservations and tests immediately before editing.
A worktree is disposable execution infrastructure, not a product, candidate or historical identity. Use canonical repo ID + commit SHA + relative paths. Current worktree diffs can warn about conflicts; a branch name alone is only a hint. Never retain a vanished directory as a permanent exclusion, or infer FREE just because it vanished: check PRs/contracts.
Argument Parsing
| Input | Meaning |
|---|---|
[path] |
Map to script --scope <repo-relative path>; keep complete families intersecting it |
--top N |
Requested final rows, default 50; fewer validated candidates is a valid result |
--validate N |
Agent-side investigation budget, default min(3 × top, 60); not a script flag |
--mode refactor|tests |
Same discovery signals; tests mode suggests COVER, never infers coverage from LOC |
--ref <ref>, --cutoff <ISO timezone> |
Freeze code SHA and history window, including for HEAD |
--engine builtin|codesift |
Stdlib estimate or verified CodeSift envelope; never compare their raw CC |
--prepare-farm <new directory> |
Export immutable inputs and worker code locally; NO measurement |
--snapshot <input.json> |
Replay a prepared DISCOVER job on the farm, without Git or credentials |
--timings, --timeout <seconds> |
Phase timings on stderr and a whole-process deadline |
--json <new file> |
Override the raw JSON destination; otherwise save in the run directory |
--no-save |
Agent-side chat-only opt-out; do not pass this flag to the CLI |
--queue <new file> |
Requires explicit REGISTER and a validated --decisions file |
--history <dir> |
Read compatible history; write only with --record-snapshot |
--no-remote |
Skip PR queries; availability UNKNOWN, not FREE |
--dry-run |
No artifacts, validation or queue creation |
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.
- 4d ago First seen · 323 lines · 71 tokens per session scan A 25d3b2cb83b4
refactor-radar is a skill published in the GitHub repository greglas75/zuvo (6 stars, last pushed 5d ago), licensed MIT. It adds 71 tokens to every session and 4,531 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 2026-09-08.
Other skills, from other repositories
kanso-commit
Use when the user asks to commit changes, stage their work, write commit messages, or split the working tree into logical commits.
kanso-pr
Use when the user asks to write a pull request description, open a PR, draft PR notes, or summarise a branch for review.
changelog
Add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
resolve-merge
Resolve an active merge or rebase conflict, including safe renumbering of colliding plans and chronicles.
commit
Create a user-requested Conventional Commit from the staged changes.
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…