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 commands/athola/skrills/create-skillgit clone --depth 1 https://github.com/athola/skrillsWrote 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/commands/athola/skrills/create-skill)<a href="https://agentmods.dev/commands/athola/skrills/create-skill"><img src="https://agentmods.dev/badge/commands/athola/skrills/create-skill.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 | $0.00016 | $0.00363 |
| Opus 5 | $0.00008 | $0.00181 |
| Sonnet 5 | $0.00003 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
create-skill 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.
What it actually says
Create Skill
Create a new skill using the skrills MCP server.
Use the mcp__plugin_skrills_skrills__create-skill tool with:
name: Name or topic for the skill (required)description: What the skill should do (required)method: Creation method - github (search), llm (generate), both, or empiricaltarget_dir: Directory to create skill indry_run: Preview without creating files
Parse $ARGUMENTS:
- First argument: skill name
- Remaining text: skill description
--method <method>or-m <method>: Creation method (default: both)--dry-runor-n: Preview mode--dir <path>: Target directory
Default behavior:
- Search GitHub for existing skills matching the name/description
- If found, offer to download and adapt
- If not found or declined, generate a new skill using LLM
Report:
- Search results (if method includes github)
- Generated skill content (if method includes llm)
- File location where skill was created
Handle errors:
- If name/description missing: Prompt for required fields
- If GitHub search fails: Fall back to LLM generation
- If target directory not writable: Report path and suggest alternative
- If skill already exists: Prompt for overwrite or new name
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 · 16 tokens per session scan A b166bec63a15
create-skill is a command published in the GitHub repository athola/skrills (69 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 363 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 commands, from other repositories
browser
Inspect and control the current AO session's target-isolated browser. The desktop app must be open. The agent and user share the same live page, cookies, navigation state, and WebContentsView; the runtime remains usable while the Browser panel is hidden. Tabs in this worker share an ephemeral browser profile, while…
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
spawn
Spawn a worker agent session in a registered project. The session runs the chosen agent in a fresh git worktree. Register the project first with ao project add.
review
Manage AO code reviews of a worker's PR.
import
Import reads the legacy Agent Orchestrator flat-file store (/.agent-orchestrator) read-only and ports its projects and per-project settings into the rewrite database. Legacy files are never modified, and a re-run skips rows that already exist, so it is safe to run more than once. The daemon must be stopped before…
learn-workspace-intent
Run Contorium BYOK workspace intent learning when API keys are configured.