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/cliffren/swf/plan-nextnpx skills add cliffren/swf --skill plan-nextgit clone --depth 1 https://github.com/cliffren/swfWhat 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 | $0.00021 | $0.00884 |
| Opus 5 | $0.00010 | $0.00442 |
| Sonnet 5 | $0.00004 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
plan-next 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Next Issues
Analyze current project state and create the next batch of issues in Linear.
Input
$ARGUMENTS — project name. Required. If not provided, ask.
Workflow
-
Load project state:
- Read
docs/design.md— what needs to be built - Read
CLAUDE.md— current phase - Read recent ADRs — any recent design decisions
- Check Linear: completed issues (what's done), remaining Todo issues (what's planned)
- Check git log: recent changes
- Read
-
Identify the gap:
- What does the current phase require (from Linear milestones + design.md)?
- What's already done?
- What's already in Todo/In Progress?
- What's missing?
-
Suggest parallelizable work from later phases:
- Some work can start before its phase is "current":
- Phase 5 的 Methods 初稿 → 核心算法确定后（Phase 1 末期）就能写
- Phase 4 的部分图 → Phase 2 有结果后就能做
- Phase 5 的 Introduction → 文献调研做过就能起草
- Present these as optional: "以下任务可以提前做，比如等实验跑的间隙："
- Mark these issues with their actual Phase milestone, not the current one
- Some work can start before its phase is "current":
-
Draft new issues:
- Default issue granularity: half-day to two-day effort (adjustable — user can ask for coarser or finer granularity)
- Smaller tasks can be combined into one issue with a checklist in the description
- Rule of thumb: if you'd want to see its status independently on the board, make it an issue; otherwise, make it a checklist item
- Include: title, description with clear acceptance criteria, labels (type + executor), milestone
- For dev tasks, reference the relevant section of design.md
- For experiment tasks, specify inputs/outputs/success criteria
-
Present to user:
## 规划：MyProject Phase 2 基于 design.md 和当前进度，建议新建以下 issues： 1. [dev, agent:codex] 实现 XX 模块的 benchmark 脚本 描述：... 2. [experiment, manual] 在数据集 A 上运行 benchmark 描述：... 3. [figures, agent:claude] 生成性能对比图 描述：... --- 可提前做（等实验间隙）--- 4. [writing, agent:claude] Methods 核心算法描述（Phase 5） 5. [figures, agent:claude] 已有 benchmark 结果可视化（Phase 4） 确认创建吗？你可以： - 合并：把几个相关的 issue 合成一个（细节放 checklist） - 拆分：把太大的 issue 拆成多个 - 修改：调整标题、描述、labels
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 · 89 lines · 21 tokens per session scan A 27d5c84a25c5
plan-next is a skill published in the GitHub repository cliffren/swf (5 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 884 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…