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/executenpx skills add greglas75/zuvo --skill executegit clone --depth 1 https://github.com/greglas75/zuvoWhat 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 | $0.00045 | $0.28804 |
| Opus 5 | $0.00023 | $0.14402 |
| Sonnet 5 | $0.00009 | $0.05761 |
| Haiku 4.5 | $0.00005 | $0.02880 |
Grade C, and why
execute scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
**User model override (`--model` in `$ARGUMENTS`) — beats the per-complexity default.** The default above quietly sends standard tasks to **Sonnet** (and reviewers/verifier to Sonnet) for cost/speed. If the user wants th How it starts
The opening of the file, as written. The whole thing — 1,544 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:execute
You are the execution orchestrator. You take an approved implementation plan and drive it to completion, task by task, with automated quality enforcement at every step.
Your role is coordination: dispatch agents, interpret their status reports, handle failures, and keep the pipeline moving. You do not write code yourself.
Environment Compatibility
Read ../../shared/includes/env-compat.md for agent dispatch patterns, path resolution, and progress tracking across all supported platforms.
Execution Modes
🔒 CODEX HARD OVERRIDE — SINGLE-AGENT ONLY (read this FIRST, it wins over everything below).
You are running on Codex. This harness has NO event-driven sub-agent wake — only wait_agent
polling — and a 28-session forensics run (2026-07-15..17) measured what thread dispatch does here:
~88h of 30s busy-polls, 19.5h/10h/8h orchestrator dead-air ended only by a human typing "kontynuuj",
sub-agents idle 78-92% of their lifetime, 747M-token context re-feeds. Therefore, on Codex:
- Every
DISPATCH <role> agent/ "dispatch per environment" / "re-dispatch the implementer" instruction in this document means: perform that role YOURSELF, inline, as a sequential checkpoint pass (same gates, same output format, same iteration caps). - Spawning agent threads or calling
wait_agentfor ANY pipeline stage is FORBIDDEN. - The "Parallel dispatch" batch rule does NOT apply — tasks run sequentially.
- If any sentence below appears to permit multi-agent on Codex, it is a build-transform artifact —
THIS block wins. Print
[MODE] single-agent (codex hard rule)once at run start.
Detect the environment per env-compat.md:
Multi-agent mode (Claude Code ONLY — that harness wakes the parent by EVENT when a sub-agent finishes; no other harness has event wake): Dispatch implementer, spec-reviewer, and quality-reviewer as separate agents. This is the preferred mode described in the execution loop below.
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 · 1,544 lines · 45 tokens per session scan C 7770cb2bcefd
execute is a skill published in the GitHub repository greglas75/zuvo (6 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 28,804 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:adopting-lib-commons-huma-wrapper
Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:opening-pull-requests
Open a GitHub Pull Request with automatic base branch detection, scope allowlist enforcement, PR template filling, and post-create base verification. Replaces ring:generating-pr-descriptions. Use after pushing a branch when ready to open a PR. Skip if the branch is not yet pushed or there are uncommitted changes …
ring:fixing-lint
Fixing lint to a clean state: runs the linter, groups reported issues into independent streams, and dispatches one parallel fixer agent per stream (ring:backend-go for Go, ring:general-purpose otherwise), iterating until clean. Use when a codebase has lint errors across multiple files. Skip for a single error (fix…