Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/greglas75/zuvonpx agentmods add skills/greglas75/zuvo/reviewWrote 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/review)<a href="https://agentmods.dev/skills/greglas75/zuvo/review"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/review/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/review"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 MCP Rug Pull · line 533 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 874 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 874 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 935 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 1126 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 | $0.00070 | $0.30618 |
| Opus 5.5 | $0.00028 | $0.12247 |
| Sonnet 5.5 | $0.00014 | $0.06124 |
| Haiku 4.5 | $0.00007 | $0.03062 |
Grade A, and why
review 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 2d 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 — 1,532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:review
Triage the diff, audit it through independent lenses, confidence-score every finding, run cross-model adversarial validation, and deliver a verdict. No separate "go" step required -- the review runs end to end.
Mandatory File Loading
PHASE 0 — Bootstrap (always, before reading any input)
1. ../../shared/includes/codesift-setup.md -- [READ | MISSING -> STOP]
This is the ONLY file loaded before reading the diff.
PHASE 0.5 — Classify (read diff, determine content type)
After CodeSift setup, read the git diff. Classify content type:
- prod-only: diff touches production files only (no
*.test.*,*.spec.*) - test-only: diff touches test files only
- mixed: diff touches both production and test files
Print: [CLASSIFIED] Diff type: {prod-only|test-only|mixed}
PHASE 1 — Conditional Load (based on diff type)
| Include | prod-only | test-only | mixed |
|---|---|---|---|
../../shared/includes/env-compat.md |
Full | Full | Full |
../../shared/includes/quality-gates.md |
CQ1-CQ40 section only* | Q1-Q25 section only** | Full |
../../shared/includes/cross-provider-review.md |
Full | Full | Full |
../../rules/cq-patterns.md or cq-patterns-core.md |
Per code type*** | SKIP | Per code type*** |
../../rules/cq-checklist.md |
TIER 1+ | SKIP | TIER 1+ |
../../rules/testing.md |
SKIP | Full | Full |
../../rules/security.md |
If security signals | SKIP | If security signals |
* CQ section only: Read from start of file to the ## Q1-Q25 heading. Skip Q section.
** Q section only: Read from ## Q1-Q25: Test Quality Gates heading to end of file. Skip CQ section.
*** cq-patterns loading rule: After Step 1 (classify code type), check the "High-Risk Gates by Code Type" table in cq-checklist.md. If the code type has <=10 relevant gates, load cq-patterns-core.md (~500 tok) instead of cq-patterns.md (~8.4K tok).
Print loaded files:
PHASE 1 — LOADED:
[list with READ/SKIP status per file and section qualifiers]
What ships with it
4 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.
- 2d ago Changed · +27 lines d0addf5212c2
- 4d ago Changed · +7 lines adfa76add382
- 8d ago Changed · +9 lines 4597d3b22bd8
- 10d ago Changed · +2 lines 790af239f498
- 14d ago Changed · +14 lines dfee3b7ab337
- 26d ago Changed · +23 lines 61771470cadc
- 28d ago Changed · +12 lines de7810ead263
- 1mo ago Changed · +80 lines a9e93425017e
- 1mo ago Changed · -2 lines 06e588632db7
- 1mo ago First seen · 1,360 lines · 70 tokens per session scan A d3e4362266c1
review is a skill published in the GitHub repository greglas75/zuvo (8 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 30,618 once invoked, about $0.0003 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.
commit
Create a user-requested Conventional Commit from the staged changes.
ring:generating-pr-descriptions
Generating pull request descriptions from git branch changes with automatic title generation, change-type detection, and smart analysis. Uses branch-only scope to avoid full history analysis. Use when preparing a PR for review. Skip when the PR is a single trivial commit or description already exists.
commit
Use when the user asks to commit changes (interactively, not inside an autonomous cycle). Runs code-simplifier + one reviewer (general code-reviewer OR the matching language reviewer, ECC agents/skills), then lint + targeted tests via evolve commit-gate run, writes a tree-SHA-bound attestation, commits + pushes via…
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.