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/stack-cairn/liveagent/skills-creatornpx skills add Stack-Cairn/LiveAgent --skill skills-creatorgit clone --depth 1 https://github.com/Stack-Cairn/LiveAgentWrote 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/stack-cairn/liveagent/skills-creator)<a href="https://agentmods.dev/skills/stack-cairn/liveagent/skills-creator"><img src="https://agentmods.dev/badge/skills/stack-cairn/liveagent/skills-creator.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00053 | $0.00708 |
| Opus 5 | $0.00026 | $0.00354 |
| Sonnet 5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
skills-creator 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 4d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Creator
Create LiveAgent-compatible skills in the fixed runtime skills root by keeping the entrypoint concise, moving long guidance into references, and using helper files only when the workflow truly needs them. Prefer English for generated skill documentation so skills stay broadly reusable, but other languages are accepted.
Workflow
- Confirm the target skill name, trigger description, captured workflow, and any required reference/helper files.
- Read
references/agent-skill-format.mdandreferences/authoring-patterns.mdthrough file tools before shaping long instructions. Usepath="skill://skills-creator/references/agent-skill-format.md"andpath="skill://skills-creator/references/authoring-patterns.md", or use the exactpathRefreturned by a prior tool. - Draft the
SKILL.mdbody in imperative form. Keep frontmatter tonameanddescriptionunless a compatibility reason requires an optional key. - Move deterministic or reusable details into
filesonly when they are truly needed; keep explanatory material inreferences/; keep output-only resources inassets/. - Use
SkillsManager(action=create)to write the skill into the fixed user skills root. Keepconflict=failunless the user explicitly wants replacement. - Use
SkillsManager(action=validate)after creation. Fix validation errors before packaging. - Use
SkillsManager(action=package)only after validation passes and a distributable archive is required. - After creation, the new skill is enabled for the current conversation automatically; ask LiveAgent to rescan skills or reopen the Skills menu only if the new skill does not appear immediately.
Rules
- Keep one skill per directory.
- Name the directory exactly after the skill name.
- Prefer English for generated skill documents, including
SKILL.md, Markdown files inreferences/, and example documentation; follow the user's language preference when they state one. - Do not add README-style files such as
README.md,INSTALLATION_GUIDE.md,QUICK_REFERENCE.md, orCHANGELOG.mdinside a skill. - Prefer one-hop references from
SKILL.md; do not build deep reference chains. - Keep the
SKILL.mdbody short enough to read comfortably throughSkillsManager. - When inspecting or optimizing files inside an enabled installed skill, use
Read,List,Glob,Grep,Write,Edit, orDeletewith the exact path you see: preferskill://<baseDir>/...or apathRefreturned by a tool. Do not use Bash for workspace or Skill file operations. - Create new skill directories through
SkillsManager(action=create)orSkillsManager(action=install). Useconflict=backuporconflict=overwriteonly when the user has accepted replacement. - Creating a skill automatically enables it for the current conversation.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 40 lines · 53 tokens per session scan A e71e22376220
skills-creator is a skill published in the GitHub repository Stack-Cairn/LiveAgent (1,913 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 708 once invoked, about $0.0003 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
himalayas-employer
AI hiring assistant for Himalayas. Post remote jobs, manage company profiles, source talent, message candidates, and benchmark salaries using the Himalayas MCP server.
che-word-mcp
A Swift-native MCP server for Microsoft Word (.docx) document manipulation. Provides 83 tools for reading, writing, and modifying Word documents without requiring Microsoft Word installation.
live-audit
Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…
live-audit
Repo-specific playbook, for any agent/model working on this repo (not tied to a particular harness — see AGENTS.md's own framing). Use it when asked to test/audit/smoke-test the published tmdb-mcp package, hunt for bugs or edge cases, or repeat "the same kind of testing as before.".
prompt-check
Live-test every MCP Prompt in src/tools/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.
prompt-check
Live-test every MCP Prompt in src/prompts.ts through the real MCP protocol (not a static read) across every argument combination, including every enum value. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.