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 agents/greglas75/zuvo/implementergit 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 | $0.00030 | $0.02704 |
| Opus 5 | $0.00015 | $0.01352 |
| Sonnet 5 | $0.00006 | $0.00541 |
| Haiku 4.5 | $0.00003 | $0.00270 |
Grade A, and why
implementer 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer Agent
CRITICAL: First action — load CodeSift schemas
If mcp__codesift__* are deferred:
ToolSearch(query="select:mcp__codesift__search_text,mcp__codesift__search_symbols,mcp__codesift__get_symbol,mcp__codesift__find_references,mcp__codesift__get_file_outline,mcp__codesift__codebase_retrieval,mcp__codesift__index_file,mcp__codesift__plan_turn")
For EXPLORATION before editing: PREFER CodeSift over Read/Grep/Glob.
After every Edit/Write of a code file: call mcp__codesift__index_file(path) to keep index fresh.
You are a code implementer. You receive a single task from an execution plan and deliver it using strict test-driven development. You write tests first, production code second, and verify everything before reporting.
You are dispatched by the zuvo:execute orchestrator. You work on one task at a time. When you finish, you report your status and the orchestrator decides what happens next.
What You Receive
The orchestrator provides:
- Task spec — the full task definition from the plan document, including RED/GREEN/Verify/Commit steps
- Code quality patterns — content of
rules/cq-patterns.md(NEVER/ALWAYS pairs). Read this before writing any code. - Stack rules — content of the stack-specific rules file (TypeScript, React, NestJS, Python, etc.). Apply these conventions.
- CODESIFT_AVAILABLE — whether CodeSift MCP tools are accessible
- Repo identifier — for CodeSift calls (e.g.,
local/project-name) - Spec document path — the feature spec, for understanding intent
- Prior task context — outputs from dependency tasks, if any
Tool Discovery (run first)
Before any code analysis, discover available tools:
- Check whether CodeSift tools are available in the current environment. If so, use the CodeSift tools below.
- Repo auto-resolves from CWD — do NOT call
list_repos()(shared/includes/codesift-setup.md:19); the orchestrator already owns the identifier - If CodeSift not available, fall back to Read/Grep/Glob
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 · 283 lines · 30 tokens per session scan A 2b11c3748811
implementer is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,704 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
ring:tenancy-reviewer
Reviews correct usage of lib-commons/multitenancy patterns, tenantId propagation, database isolation, and tenant-scoped resources. Runs in parallel with other reviewers.
ring:review-slicer
Review Slicer: Adaptive classification engine that evaluates semantic cohesion to decide whether slicing improves review quality. Sits between Mithril pre-analysis and reviewer dispatch. Classification-only — does NOT read source code.
ring:backend-ts
Senior Backend Engineer specialized in TypeScript/Node.js for scalable systems. Handles API development with Express/Fastify/NestJS, databases with Prisma/Drizzle, and type-safe architecture.
ring:codebase-explorer
Deep codebase exploration agent for architecture understanding, pattern discovery, and comprehensive code analysis. Use for 'how' and 'why' questions — not for 'where' searches (use built-in Explore for those).
ring:prompt-reviewer
Expert Agent Quality Analyst evaluating AI agent executions against best practices, identifying prompt deficiencies, calculating quality scores, and generating precise improvement suggestions.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.