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/nokonoko1203/claude-code-settings/kill-dev-processnpx skills add nokonoko1203/claude-code-settings --skill kill-dev-processgit clone --depth 1 https://github.com/nokonoko1203/claude-code-settingsWhat 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 | $0.00043 | $0.00985 |
| Opus 5 | $0.00022 | $0.00492 |
| Sonnet 5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
kill-dev-process 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 3d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Environment Cleanup
Safely clean up processes accumulated during development (dev servers, browsers, node, etc.).
Usage: /kill-dev-process
Usage: /kill-dev-process $MODE
$ARGUMENTS to specify mode:
ports— Only processes occupying listening portsbrowsers— Only browser processesall— Process all categories at once- No argument — Interactive selection
Execution Steps
Step 1: Investigate the Current State
Run the following commands in parallel to assess the current situation:
# List listening TCP ports (macOS)
lsof -iTCP -sTCP:LISTEN -P -n 2>/dev/null | grep -v "^COMMAND"
# Dev-related node processes
ps aux | grep -E '[n]ode|[t]sx|[v]ite|[n]ext|[n]uxt|[e]sbuild|[t]sc |[b]un ' | grep -v 'grep'
# Browser processes (including those from Playwright/Chrome DevTools MCP)
ps aux | grep -E '[C]hromium|[c]hrome|[C]hrome Helper|[p]laywright' | grep -v 'grep'
Step 2: Classify and Display Results
Classify detected processes into the following categories and display in table format:
| Category | Criteria |
|---|---|
| Dev Servers | Processes listening on ports 3000-9999 via node/bun/deno |
| Browsers | Chromium, Chrome, Playwright-related processes |
| Build Tools | Residual esbuild, tsc, webpack, turbopack, etc. |
| Other | Anything else requiring user confirmation |
Display format example:
## Detected Processes
### Dev Servers (3 items)
PID PORT COMMAND STARTED
12345 3000 node next-server 10:30
12346 5173 node vite 11:45
12347 8080 node express 09:00
### Browsers (5 items)
PID COMMAND MEM
23456 Chromium --headless 120M
23457 Chrome Helper (Renderer) 80M
...
Step 3: Safety Check
Processes that must NEVER be killed:
- System processes (PID < 100, root-owned system daemons)
- Databases (postgres, mysql, redis, mongo)
- Docker / containerd
- SSH / sshd
- IDE itself (VSCode, Cursor) — Chrome helpers ARE eligible targets
- Long-running processes that appear to be intentionally started by the user
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.
- 3d ago First seen · 124 lines · 43 tokens per session scan A 1d496d3e8872
kill-dev-process is a skill published in the GitHub repository nokonoko1203/claude-code-settings (92 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 985 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 2026-08-30.
Other skills, from other repositories
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
social-post
學習使用者的 Facebook/Instagram/YouTube/Threads/X 語氣與受眾,規劃、撰寫、確認後發佈內容;以已登入 Chrome 受控掃描、草擬及回覆 FB/IG/Threads 留言;並作為流量、留存與轉化的結構化帳本。使用者說「發文」「用我的口氣」「回覆留言」「自動回留言」「掃留言」「查流量」「演算法」「把數據訓練進去」「比較貼文」「優化 pattern」時使用。.
privacy-eu
EU 사용자 대상 서비스용 Privacy Notice·Terms of Service·Consent Modal·Cookie Banner 자동 생성. GDPR (Regulation 2016/679) + ePrivacy Directive + Consumer Rights Directive 2011/83 + Digital Services Act + Digital Content Directive + Unfair Terms Directive 반영. 영문 인터뷰로 진행.
privacy-terms
처리방침·이용약관 자동 생성 진입점. 호출 즉시 6개 하위 스킬(privacy-kr·privacy-eu·privacy-us·privacy-jp·privacy-global·privacy-global-jp)을 번호 메뉴로 제시하고, 번호 입력 즉시 해당 스킬 인터뷰로 직행한다.
higgsfield-troubleshoot
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.
higgsfield-motion-design
End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion', 'motion design', 'animate this', 'make a video…