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/andrewcigan/vibe-dev-plugin/synthesizergit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWrote 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/agents/andrewcigan/vibe-dev-plugin/synthesizer)<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>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 | $0.00062 | $0.01332 |
| Opus 5 | $0.00031 | $0.00666 |
| Sonnet 5 | $0.00012 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
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.
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
- Read оба input файла
- Объединить тесты по категориям (happy / edge / error / e2e)
- При совпадении — merge в один тест с лучшим описанием
- При конфликте — user-perspective wins (record reason)
- Write
docs/test-strategy.md - Обновить
feature_list.json[active].verification.layer_1..4
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 · 148 lines · 62 tokens per session scan A 113d18b985ba
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.
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.…
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.
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…
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…
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…
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…