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/aidyou/chatspeed/commitnpx skills add aidyou/chatspeed --skill commitgit clone --depth 1 https://github.com/aidyou/chatspeedWhat 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 | $0.00025 | $0.00427 |
| Opus 5 | $0.00013 | $0.00214 |
| Sonnet 5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
commit 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 yesterday.
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
Commit
Create a local Git commit with real Git commands and a Conventional Commit message.
Workflow
- Inspect Git status, staged files, recent commits, and the relevant diff.
- Keep unrelated changes out of the commit. Ask before including unclear changes or splitting commits.
- Check candidate paths and diffs for sensitive data.
- Run checks only when the user explicitly requests them.
- Stage the intended files and create the commit.
- Report the commit and any checks that actually ran.
Optional Verification
Do not run lint, tests, builds, typechecks, or documentation generation just because the user asked for a commit. A local commit is not a push or CI gate.
Run a check only when the user explicitly requests testing or verification. Use the narrowest relevant existing project command.
Staging Rules
If files are already staged, commit only those files unless instructed otherwise. Otherwise, stage only files belonging to the requested change. Never discard, reset, clean, or overwrite existing changes.
Commit Message
Match the recent repository style and language. Use:
<type>[optional scope]: <concise description>
Keep the subject under 72 characters and state the key change. Add a short body only when it is needed to explain an important behavior change, compatibility impact, or breaking change. Do not add exhaustive implementation detail.
Sensitive Data Review
Before staging, inspect candidate files and diffs for secrets, credentials, private keys, tokens, connection strings, local databases, or data exports. If a possible secret is found, stop and ask the user whether to exclude or explicitly include each affected file.
Safety
- Use real Git commands; do not call a nonexistent custom commit command.
- Do not create branches, stashes, resets, checkouts, cleanups, or pushes without explicit approval.
- Create a commit only when the user explicitly asks for one.
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.
- yesterday First seen · 50 lines · 25 tokens per session scan A 70db4232f9f6
commit is a skill published in the GitHub repository aidyou/chatspeed (21 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 427 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 2026-08-30.
Other skills, from other repositories
copilot-setup-audit
Audit repository Copilot customization setup. Use this skill to analyze existing configuration, identify missing files, check for best practices, and suggest improvements for agents, prompts, instructions, and skills.
copilot-compatibility-checker
Check VS Code and GitHub Copilot feature compatibility. Use this skill when diagnosing why a feature isn't working, checking required settings, or verifying version requirements for experimental features.
copilot-skill-builder
Create and maintain Agent Skills for VS Code and GitHub Copilot. Use this skill when setting up new skills, skill directories, or SKILL.md files. Helps scaffold project skills in .github/skills/ or personal skills in /.copilot/skills/.
notebooklm
Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X".
forensic-transcript-translator
法證級美股電話會議逐字稿翻譯工具，含獨立交叉審計。五階段流程：結構指紋提取 → 動態術語鎖定 → 嚴格逐字翻譯 → 獨立 subagent 法證審計 → 組裝輸出。確保 100% 零遺漏、零曲解。使用時機：(1) 使用者提供英文 earnings call 逐字稿檔案並要求翻譯成繁體中文, (2) 使用者要求「法證翻譯」或「forensic translate」, (3) 使用者要求翻譯長篇（超過 2000 字）財報電話會議逐字稿且強調不可遺漏。與 taiwan-earnings-translator 的差異：本技能增加「結構指紋比對」與「獨立 subagent 交叉審計」，適用於對完整性有嚴格要求的場景。.
rem
管理 macOS Reminders。處理「提醒我 XXX」「記一下 XXX」等中文自然語言指令，支援 briefing 待辦整合。當用戶提及提醒事項、待辦、Reminders、或要建立/查詢/完成/刪除提醒時使用。.