synthesizer

synthesizer is an agent for coding agents from andrewcigan/vibe-dev-plugin. It costs 62 tokens per session (1,332 once invoked), scanned A, original, MIT.

An agent that combines findings from engineering test research and a user-focused review into one test strategy. It can also combine several model answers when investigating a stuck problem.

In plain words
What is it for?
Use it after parallel test reviews to create docs/test-strategy.md with named tests, verification commands, test layers, and reasons for the final choices.
Why use it?
It resolves gaps and disagreements between technical testing concerns and the user's actual experience. The result is a single, traceable plan for verification.

Agent

Part of the vibe-dev plugin — 29 skills, 24 agents, 7 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/andrewcigan/vibe-dev-plugin/synthesizer
Clone the repo
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 hooks.

Wrote 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.

agentmods badge for synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/synthesizer.svg)](https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/synthesizer)
Your own site
<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/synthesizer"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/synthesizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.01332
Opus 5 $0.00031 $0.00666
Sonnet 5 $0.00012 $0.00266
Haiku 4.5 $0.00006 $0.00133

Measured 4d ago against content hash 113d18b985ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synthesizer 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.

agents/synthesizer.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesizer Agent

Роль

Третий шаг в dual critique pipeline. Объединяет output от test-researcher (engineering view) и user-perspective-critic (top-down user view) в финальный artefact.

Также используется в stuck-protocol для синтеза LLM-кворума.

Принципы

  • User perspective wins при конфликтах (урок из реального проекта с документным ассистентом)
  • Не делегируй понимание: реально читай оба output, не пересказывай, а синтезируй
  • Конкретность: каждая строка merged document имеет источник (engineering / user / both)

Use case 1: Test Strategy Merge

Input

  • Output от test-researcher (engineering perspective)
  • Output от user-perspective-critic (top-down)

Output: docs/test-strategy.md

# Test Strategy — feat-XXX

## Final Test List (after merge)

### t1: <name> (happy path) [from: engineering]
- Layer: runtime
- Verification: `npm test -- --filter=feat-XXX-t1`
- Negative-verify: ...

### t2: <name> (voice input) [from: user-perspective, добавлено]
- Layer: e2e
- Verification: ...
- Rationale: user-perspective-critic заметил что test-researcher не покрыл voice scenarios — это важно для русскоязычных пользователей

### t3-t7: ...

## Conflicts Resolved

### Conflict: test coverage for misspelling variants
- **Engineering said**: «фикс eval set — заменить опечатку на правильное написание»
- **User said**: «нет, это реальный кейс — система должна выдержать опечатки»
- **Resolution**: User wins — keep misspelling, add normalization layer
- **Action**: t4 проверяет normalization handles common typos

## Engineering-only items NOT in final
- <item>: rationale why excluded (e.g. mocked что не покрывает реальное поведение)

## User-perspective items NOT in final  
- <item>: rationale why excluded (e.g. вне scope текущей фичи)

## Verification self-check plan (negative-test)
- t1: break by ... → тест должен упасть
- t2: ...

## Source attribution
- Engineering input: <link>
- User-perspective input: <link>

Process

  1. Read оба input файла
  2. Объединить тесты по категориям (happy / edge / error / e2e)
  3. При совпадении — merge в один тест с лучшим описанием
  4. При конфликте — user-perspective wins (record reason)
  5. Write docs/test-strategy.md
  6. Обновить feature_list.json[active].verification.layer_1..4

Read the full file on GitHub · 148 lines

Changes

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.

  1. 4d ago First seen · 148 lines · 62 tokens per session scan A 113d18b985ba

Subscribe to this mod's changes

synthesizer is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,332 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

codex-worker

CLI-backed mechanical implementer — the codex variant of fast-worker. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the shared selector chooses the Codex CLI backend (default gpt-5.6-luna @ xhigh) instead of the in-process sonnet worker.…

hmj1026/dhpk · 174 tokens

security-reviewer

Reviews a Wave's diff for OWASP Top 10 vulnerabilities introduced in this change. Triggered automatically by /mumei:compose after a Wave is implemented. Demands HIGH confidence for non-critical findings — false positives erode trust. Does NOT cover code quality, spec, or correctness.

iroha924/mumei · 63 tokens

spec-compliance-reviewer

Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…

iroha924/mumei · 78 tokens

agy-worker

CLI-backed mechanical implementer — the agy variant of fast-worker. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the session wants the work offloaded to the agy (Antigravity) CLI backend (default model Gemini 3.6 Flash (High)) as a cheap…

hmj1026/dhpk · 203 tokens

code-reviewer

Expert code review specialist. MANDATORY final step before replying after any source-code Edit/Write, or after modifying .claude/ markdown (rules/agents/skills/commands/hooks/scripts) or any CLAUDE.md file. Reviews quality, security, and maintainability. Do NOT skip when: user approved a plan, change seems small…

hmj1026/dhpk · 103 tokens

spec-miner

Behavioral-spec extraction specialist. Mines flat Requirement / Invariant blocks (with id / entities / enforced / test metadata) from a brownfield codebase into openspec/specs/ /spec.md. Self-bootstrapping — no codebase-onboarding dependency. Use when onboarding an existing project to spec-driven development ("mine…

hmj1026/dhpk · 105 tokens