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 skills add aidyou/chatspeed --skill helpgit clone --depth 1 https://github.com/aidyou/chatspeedWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aidyou/chatspeed/help)<a href="https://agentmods.dev/skills/aidyou/chatspeed/help"><img src="https://agentmods.dev/badge/skills/aidyou/chatspeed/help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aidyou/chatspeed/help"><img src="https://agentmods.dev/badge/skills/aidyou/chatspeed/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00068 | $0.01589 |
| Opus 5.5 | $0.00027 | $0.00636 |
| Sonnet 5.5 | $0.00014 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
help 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 21d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatSpeed Help and Capability Skill
This is the only bundled capability Skill besides commit. It combines official product documentation with the operational guidance for Agent Skills, MCP servers, and the cscli CLI.
AI Assistant Instructions
When a user asks a question about ChatSpeed:
- Check the Index: Scan the "Documentation Index" and "Capability Operations" sections below.
- Fetch Details: For product documentation or troubleshooting, use the
web_fetchtool to retrieve the actual content from the corresponding URL (Base URL:https://docs.chatspeed.aidyou.ai/). - Use capability operations: For local Skills or MCP management, use the existing capability operations and report their structured result. Do not guess an external tool's directory or write to an unverified path.
- Synthesize: Provide a concise answer based on the official documentation or operation result. Include the source link when documentation was fetched.
- Fallback: If the question is not covered or fetching fails, direct the user to
https://docs.chatspeed.aidyou.ai/.
Built-in CLI Invocation
cscli is short for ChatSpeed CLI. Inside ChatSpeed, invoke it directly through the bash tool as a standalone command, for example cscli skill targets. ChatSpeed automatically resolves this command to the bundled executable and runs it on the host; it does not rely on shell PATH lookup.
The bundled CLI is not automatically added to PATH. Do not use which cscli, command -v cscli, or similar shell lookup commands to locate or validate it: they do not test ChatSpeed's built-in resolution. Do not substitute a PATH executable or fall back to the old cs name. Outside ChatSpeed, use the bundled executable's explicit path unless you have separately configured PATH.
Prefer standalone commands without shell operators. A trailing 2>&1 is accepted for compatibility and ignored because the tool already captures stdout and stderr. Pipelines, other redirects, environment prefixes, and chained commands are not supported by built-in resolution. If a direct invocation fails, report the actual error instead of searching for another executable. Automatic resolution does not bypass approval for mutating operations.
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.
- 21d ago Changed · +8 lines 79f082212a2e
- 24d ago Changed · +45 lines · +42 tokens per session 2b873f735655
- 1mo ago First seen · 54 lines · 26 tokens per session scan A 92fe6e8fe26f
help is a skill published in the GitHub repository aidyou/chatspeed (21 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,589 once invoked, about $0.0003 per session on Opus 5.5. 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
A multi-stage workflow for translating a long English earnings-call transcript into Traditional Chinese used in Taiwan. It records the transcript structure and uses separate checks to compare the original and translation for missing or altered content.
taiwan-earnings-translator
A Traditional Chinese translator for complete U.S. stock earnings-call transcripts, including transcripts supplied as text or English PDFs. Earnings calls are company presentations and question sessions about financial results.