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/cookys/autopilot/nextnpx skills add cookys/autopilot --skill nextgit clone --depth 1 https://github.com/cookys/autopilotWhat 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 | $0.00102 | $0.01439 |
| Opus 5 | $0.00051 | $0.00720 |
| Sonnet 5 | $0.00020 | $0.00288 |
| Haiku 4.5 | $0.00010 | $0.00144 |
Grade B, and why
next scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`cat .claude/next-config.md 2>/dev/null || true` How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next — Work Recommender Engine
Routing overlap? If this intent better matches a sibling skill, redirect per references/routing-tiebreaks.md (prefer backlog scanning over strategic prioritization debate).
Scan all work sources, present categorized results, converge to a single recommendation.
Project Config (auto-injected)
!cat .claude/next-config.md 2>/dev/null || true
Trigger
| Trigger | When | Notes |
|---|---|---|
| Auto | After autopilot:project-lifecycle completes |
Replaces old Backlog Pickup |
| Manual | User types /next |
Any time |
| Deep | /next --deep |
Forces C-level scan |
Scan Depth (Adaptive)
Read .claude/next-state.json to determine depth.
| Level | Condition | Scope | Time |
|---|---|---|---|
| A | Default | Structured data (INDEX/BACKLOG/plans/proposals) | Seconds |
| B | Last A > 12 hours ago | A + skill sizes, knowledge staleness, MEMORY.md size | 10-30s |
| C | /next --deep |
B + git log cold zones, TODO/FIXME stats, deploy drift | 1-2 min |
Update .claude/next-state.json after each scan with ISO timestamps.
Execution Flow
Phase 0: Hygiene (Silent)
Process accumulated digests and improvement-queue without user interaction. Details: references/phase0-hygiene.md
Phase 1: Scan All Sources
| Category | Source | Method |
|---|---|---|
| Dev | docs/projects/INDEX.md |
Find in-progress projects' next Phase |
docs/plans/INDEX.md |
Find plans in design stage | |
docs/BACKLOG.md |
Check if trigger conditions are met | |
docs/proposals/ |
List pending proposals | |
| Maintenance | improvement-queue.json |
Pending items (from Phase 0) |
[B] skills/*/SKILL.md |
Skills > 200 lines | |
| [B] MEMORY.md | > 170 lines | |
[B] ~/.autopilot/distill/scan-state.json |
mtime > 14 days OR file missing (scan never ran) → list "distill frequency scan overdue" under Maintenance | |
| Knowledge | session-digests/ |
Phase 0 results |
[B] knowledge/*.md |
last-verified > 30 days |
|
| Tech Debt | docs/BACKLOG.md tech-debt |
List all (even unmet triggers) |
[C] src/ |
TODO/FIXME count | |
[C] git log --since="30 days ago" |
Untouched src/ subdirectories |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 135 lines · 102 tokens per session scan B cec03b893f9a
next is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session and 1,439 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.