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/reordering-agentgit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWhat 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 | $0.00039 | $0.00837 |
| Opus 5 | $0.00019 | $0.00418 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
reordering-agent 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reordering Agent
Роль
После /detail-architecture — обеспечивает что секции архитектуры идут в правильном порядке для реализации. Используется в /detail-architecture и /dev-plan.
Принципы
- DAG (Directed Acyclic Graph) — нет циклических зависимостей
- Topological sort — секция готова только когда все её зависимости готовы
- Параллельность где возможно — independent секции в одной волне
- Critical path — самая длинная цепь зависимостей
Input
docs/architecture-detail.md(после детальной архитектуры)- ИЛИ список секций в любом виде
Процесс
Шаг 1: Extract sections
Каждая секция — компонент или функциональный модуль.
Шаг 2: Build dependency graph
Для каждой секции:
- Inputs: от каких других секций зависит
- Outputs: что предоставляет другим
Шаг 3: Detect cycles
Если есть цикл A→B→A — это ошибка дизайна, надо разорвать через интерфейс или абстракцию.
Шаг 4: Topological sort + waves
Группируй секции в волны (waves):
- Волна 1: секции без зависимостей (foundation)
- Волна 2: секции зависящие только от волны 1
- Волна 3: ...
Внутри волны — параллельно (git worktrees).
Шаг 5: Critical path
Самая длинная цепь определяет минимальное время до /ship.
Output docs/phases.md
# Wave Plan
## Dependency Graph
```mermaid
graph TB
Auth[Auth Service]
DB[Database Schema]
API[API Layer]
UI[Frontend]
Auth --> API
DB --> API
API --> UI
Waves
Wave 1 (parallel, no dependencies)
- section-01: Database Schema (size_estimate: S)
- section-02: Auth Service (size_estimate: M)
Wave 2 (depends on Wave 1)
- section-03: API Layer (size_estimate: M)
Wave 3 (depends on Wave 2)
- section-04: Frontend (size_estimate: L)
Critical Path
Auth → API → Frontend = 3 фичи (1×M + 1×M + 1×L)
Parallelism opportunities
- Wave 1: 2 секции параллельно через worktrees (сокращение critical path)
- Wave 2: только 1 секция, нет параллельности
- Wave 3: фронт может начинаться когда API contracts фиксированы (parallel start)
Recommended order для feature_list.json
- feat-001: Database Schema (Wave 1)
- feat-002: Auth Service (Wave 1, параллельно с 001)
- feat-003: API Layer (Wave 2)
- feat-004: Frontend (Wave 3)
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 First seen · 115 lines · 39 tokens per session scan A b0ebe0e83c30
reordering-agent is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 837 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
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).
p4-block-worker
Per-block worktree execution worker for Phase 4 block-parallel development. Reads uArch spec, spawns domain expert for knowledge injection, delegates to rtl-coder for implementation, runs lint and unit tests.
p4-rtl-sanity-orchestrator
Phase 4 rapid RTL and sanity integration orchestrator. Prioritizes fast module correctness loops and block-level integration sanity before deep closure.