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/ideanpx skills add cliffren/swf --skill ideagit 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 | $0.00017 | $0.01717 |
| Opus 5 | $0.00009 | $0.00859 |
| Sonnet 5 | $0.00003 | $0.00343 |
| Haiku 4.5 | $0.00002 | $0.00172 |
Grade A, and why
idea 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Research Idea
Create a new research idea in the Linear Ideas project and set up standard evaluation sub-issues.
Input
$ARGUMENTS — the name/title of the research idea. If not provided, ask the user.
Workflow
-
Create the main issue in the Ideas project:
- Title:
$ARGUMENTS - Status: Todo
- Ask the user for a 1-2 sentence description of the idea
- Title:
-
Discuss and clarify the idea with the user before creating sub-issues:
- Ask one question at a time:
- "这个想法要解决什么问题？"
- "和现有方法/工具的区别是什么？"
- "大致的技术思路是什么？"
- "预期的贡献是什么？（方法创新？性能提升？新应用？）"
- Summarize the discussion into a clear idea statement
- Save to
~/Projects/ideas/<idea-slug>/idea-statement.md - Update the main issue description with the idea statement
- Ask one question at a time:
-
Create evaluation sub-issues under the main issue:
Sub-issue Labels Output template 文献调研：领域进展、找到 gap writing,agent:claudesee below 评估意义/创新性/可行性 writing,agent:claudecopy key insights into literature-review.md, keep feasibility.md as-is 技术选型 writing,agent:claude撰写 design.md 初稿 writing,agent:claude画框架图初版 figures,agent:claude -
Create local workspace:
- Create directory:
~/Projects/ideas/<idea-slug>/ - This is NOT a git repo, just a local workspace for evaluation drafts
- Evaluation outputs go here as markdown files:
~/Projects/ideas/<idea-slug>/ ├── idea-statement.md ← 想法讨论梳理 ├── literature-review.md ← 文献调研 ├── feasibility.md ← 可行性评估 ├── tech-selection.md ← 技术选型 ├── design.md ← design.md 初稿 └── framework.svg ← 框架图 - After each sub-issue is done, post a brief summary (3-5 sentences) as a Linear issue comment, with detailed content in the local file
- When
/swf:promoteruns, it migratesdesign.mdandframework.svginto the new repo
- Create directory:
-
Set up evaluation order:
- The sub-issues have dependencies:
① 文献调研 → ② 评估可行性 → ③ 技术选型 → ④ design.md 初稿 ⑤ 框架图（独立，不阻塞，Backlog） - Note: idea discussion (step 2) happens BEFORE sub-issues are created, so it's not a sub-issue
- ①~④ set to Todo, with blocking relations: ② blocked by ①, ③ blocked by ②, ④ blocked by ③
- ⑤ 框架图 set to Backlog — optional during evaluation, can be done if time permits or deferred to after promote
- The sub-issues have dependencies:
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 · 155 lines · 17 tokens per session scan A d3f75b164952
idea is a skill published in the GitHub repository cliffren/swf (5 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,717 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…