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 skills/andrewcigan/vibe-dev-plugin/dev-plannpx skills add andrewcigan/vibe-dev-plugin --skill dev-plangit 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 | $0.00071 | $0.00653 |
| Opus 5 | $0.00036 | $0.00327 |
| Sonnet 5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
dev-plan 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.
What it actually says
/dev-plan
Wave-план через dev-planner agent.
Что происходит
- Subagent
dev-planner(Opus) читает architecture-detail.md, phases.md, domain-rules - Map sections → features в feature_list.json
- Каждая feature получает:
- id, name, description, wave
- dependencies (от каких других)
- size_estimate (S/M/L → light/heavy path в /feature)
- affected_files явно
- verification (4-layer)
- business_invariant ссылка на domain-rules.invariants
- budget_usd
reordering-agentвалидирует DAG (нет циклов)
Output
- Обновлённый
feature_list.json(captured + up_next) docs/ROADMAP.md
Stage verifier
- Все features имеют affected_files
- Все features имеют verification
- DAG без циклов
- Total budget ≤ monthly_total_budget_usd
Дальше
/validation-sample — строим эталонную выборку.
После — /feature feat-001 (первая фича из Wave 1).
Финальное сообщение (обязательный формат)
Финализируй шаблоном B (см. rules/message-finalization.md):
Готово. Wave-план: 8 фичей в 3 волнах, docs/ROADMAP.md обновлён.
Волна 1 (parallel, 2 фичи): foundation (database + auth)
Волна 2 (зависит от 1, 3 фичи): API + business logic
Волна 3 (зависит от 2, 3 фичи): UI + integrations
Объём: 8 фичей (5×M + 3×L). Critical path: 5 фичей.
LLM-cost оценочно: ~$X на all features.
Внешняя рамка поставки клиенту: <из cost_policy / domain-rules>.
Вопросов от меня нет. Следующий шаг — /validation-sample (эталонная выборка 50-100 сценариев). Согласен?
НЕ оценивать в человеко-днях. См. rules/no-human-days.md — используем количество фичей + size_estimate (S/M/L). Внешний дедлайн клиента в днях — допустим только как «внешняя рамка поставки», не «бюджет нашей работы».
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 · 62 lines · 71 tokens per session scan A 1a05c5304983
dev-plan is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 653 once invoked, about $0.0004 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 skills, from other repositories
harness-engineering-guide
Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
github-gitlab
Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.