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 HybridAIOne/hybridclaw --skill hybridclaw-helpgit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/hybridclaw-help)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/hybridclaw-help"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/hybridclaw-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/hybridaione/hybridclaw/hybridclaw-help"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/hybridclaw-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 | $0.00030 | $0.01093 |
| Opus 5 | $0.00015 | $0.00547 |
| Sonnet 5 | $0.00006 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
hybridclaw-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 12d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HybridClaw Help
Use this skill for product-specific HybridClaw questions such as:
- how to configure a feature
- where config lives
- what a command does
- how a subsystem behaves
- what changed in a recent release
- where a documented workflow is described
This is the default skill for HybridClaw product questions. Prefer it over generic service skills when the question is about HybridClaw itself, its built-in features, its channel integrations, or its documented configuration.
Core Rule
For HybridClaw behavior, commands, configuration, architecture, release notes, or runtime locations: consult public docs URLs first. Do not assume repo source files are present in the current workspace. npm installs may include packaged docs, but the agent may still only have direct access to web URLs.
Use web_fetch or web_extract against the public docs site or raw GitHub URLs
before answering from memory.
Canonical Sources
Start with the narrowest relevant source from this list:
https://www.hybridclaw.io/docs/agents.mdhttps://www.hybridclaw.io/docs/?search=<terms>https://www.hybridclaw.io/docs/agents.md?search=<terms>https://www.hybridclaw.io/docs/reference/configurationhttps://www.hybridclaw.io/docs/reference/commandshttps://www.hybridclaw.io/docs/https://www.hybridclaw.io/docs/https://raw.githubusercontent.com/HybridAIOne/hybridclaw/main/config.example.jsonhttps://raw.githubusercontent.com/HybridAIOne/hybridclaw/main/README.mdhttps://raw.githubusercontent.com/HybridAIOne/hybridclaw/main/CHANGELOG.md
Only widen into implementation files when the docs are missing, incomplete, or
ambiguous. If code inspection is required, use local package files when they are
directly accessible; otherwise use GitHub source URLs instead of assuming src/
exists in the workspace.
Default Workflow
- Identify the question type: config, command, behavior, architecture, or release history.
- Fetch the most likely public doc or raw GitHub source first.
- If the right page is not obvious, use the docs search URL with a narrow query.
- If needed, confirm with the matching implementation file or GitHub source instead of guessing.
- Answer narrowly and concretely.
- Include the exact config keys, command names, URLs, file paths, or version headings that support the answer.
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.
- 12d ago First seen · 104 lines · 30 tokens per session scan A 5b6295e14c36
hybridclaw-help is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,093 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
m3-notify
Poll the inbox for new notifications addressed to you.
Hooks Automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
conventional-commit
Workflow for generating conventional commit messages following the Conventional Commits specification. MUST be invoked every time a commit is created. Guides construction of standardized commit messages with correct type, scope, description, body, and footer.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.