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/threat-vector-security/guardian-agent/skill-creatornpx skills add Threat-Vector-Security/guardian-agent --skill skill-creatorgit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/skill-creator)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/skill-creator"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/skill-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 5.1 | $0.00051 | $0.00716 |
| Opus 5 | $0.00026 | $0.00358 |
| Sonnet 5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
skill-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 6d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Treat skill work as an eval-driven workflow: understand real usage, draft the skill, test trigger behavior, compare against baseline behavior, and refine it.
Start With Intent
Extract as much as possible from the current conversation before asking for more:
- what the skill should help with
- when it should trigger
- what good output looks like
- whether the task needs deterministic evals or mostly qualitative review
When the workflow is still vague, capture 2-3 realistic user prompts before writing the skill.
Drafting Rules
- Put trigger guidance in the frontmatter description, not only in the body.
- Make the description describe when to use the skill, not the full workflow inside the skill.
- Prefer trigger symptoms and task conditions over abstract labels.
- Keep the skill body procedural and easy to scan.
- Move large supporting material into
references/,templates/, orexamples/. - Keep
SKILL.mdfocused on the workflow. Put heavy reference content inreferences/. - If the skill is imported or adapted from a third-party source, preserve provenance and license notices in
THIRD_PARTY_NOTICES.md.
Trigger Authoring
- Write the description as activation guidance, not marketing copy.
- Treat the description field as model-facing trigger text; keep it high-signal because the runtime scores it alongside explicit keywords.
- Include the user signals that should cause the skill to trigger.
- Include nearby non-trigger cases when they are easy to confuse.
- Prefer concrete request language over broad nouns like "help", "workflow", or "tool".
- Keep automatically matched keywords narrow; generic words create noisy false positives.
- If the skill should rarely auto-select, prefer explicit mention and description fallback over a wide keyword list.
Improvement Loop
- Draft or revise the skill.
- Write 2-3 realistic test prompts.
- Compare with-skill behavior against a baseline when possible.
- Check two things separately:
- Did the skill trigger when it should?
- Did the full skill body improve behavior after triggering?
- Capture what improved, what regressed, and what still feels vague.
- Tighten the description and instructions, then test again.
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.
- 6d ago First seen · 68 lines · 51 tokens per session scan A c389851b90c2
skill-creator is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 716 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
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
continuum-handoffs
Build agent-to-agent transitions with Continuum's Handoff system — triage routing, history summarization modes (FULL/SUMMARY/RECENTN/HYBRID), cycle detection, depth tracking, return-to-parent. Invoke when the user asks "route customer requests to specialists", "agent that can transfer to another", "summarize history…
continuum-llm-providers
Pick the right LLM provider, configure structured outputs, control context-window compression, and use the LLMClient directly. Provider routing is by model-string prefix; LiteLLM has been removed. Also covers Smart Gateway integration for multi-provider routing. Invoke when the user asks about "switch to Claude"…
continuum-testing
Write tests for Continuum agents — mock LLM and memory clients via the DI Container, use fakeredis for sessions, snapshot agent responses, and run pytest-asyncio. Invoke when the user asks "test my agent", "mock the LLM", "fakeredis", "container injection", "pytest", or wants their CI to validate agent behavior…
continuum-streaming
Stream tokens, tool calls, handoffs, and memory events out of a Continuum agent in real time using runner.runstream() and the EventType enum. Invoke when the user asks "stream tokens to UI", "websocket chat", "live progress", "see tool execution as it happens", or anything that needs token-by-token output.