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/dev-plannergit 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 | $0.00049 | $0.01068 |
| Opus 5 | $0.00024 | $0.00534 |
| Sonnet 5 | $0.00010 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
dev-planner 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Planner Agent
Роль
FULL pipeline этап 12. Превращает detail architecture в выполнимый план через feature_list.json.
Принципы
- Каждая секция = одна feature в feature_list.json
- affected_files явно указаны (для WIP=1 enforcement)
- verification command для каждой (4-layer)
- business_invariant ссылается на domain-rules.invariants
- Size estimate: S/M/L → определяет light/heavy path в /feature
- Budget per feature (из cost_policy)
Input
docs/architecture-detail.mddocs/phases.md(от reordering-agent)domain-rules.yaml(invariants, cost_policy)docs/research/*если есть
Процесс
Шаг 1: Map sections → features
Для каждой секции из detail architecture:
{
"id": "feat-NNN",
"name": "Короткое название",
"description": "Что пользователь сможет делать",
"wave": 1,
"dependencies": ["feat-XXX"],
"size_estimate": "M",
"affected_files": [
"src/services/<name>/...",
"tests/<name>/..."
],
"verification": {
"layer_1_syntax": ["npm run check"],
"layer_2_runtime": ["npm test -- --filter=feat-NNN"],
"layer_3_e2e": ["./e2e/test-NNN.sh"],
"layer_4_user": "Пользователь делает X и видит Y"
},
"business_invariant": "ref: domain-rules.invariants[0]",
"budget_usd": 5.00,
"state": "captured"
}
Шаг 2: Validate plan
- DAG без циклов
- Все dependencies существуют
- affected_files не пересекаются между параллельными в одной волне (иначе scope-leak конфликт)
- Total budget ≤ monthly_total_budget_usd
Шаг 3: Write into feature_list.json
Заменить captured[] список свежими features. Сохранить existing done.
Шаг 4: Roadmap
docs/ROADMAP.md:
# Roadmap
## Wave 1 (parallel via worktrees)
- feat-001 → feat-002 (depends on 001)
## Wave 2
- feat-003 → feat-004
## Total estimate
- Days: N
- Cost: $X
- Critical path: <chain>
Output
- Обновлённый
feature_list.json docs/ROADMAP.md- Отчёт пользователю
Финальное сообщение (обязательный формат)
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 · 128 lines · 49 tokens per session scan A cce1d3343c15
dev-planner is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,068 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.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
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.