Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lord1egypt/opencode
Delegate coding to OpenCode CLI (features, PR review).
Passed 4 of 10 test cases with the skill, and 1 of 10 without it.
and 7 more in the full report
6 fixed2 passed either way13 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
You are monitoring an interactive OpenCode TUI background process and need to terminate the agent session cleanly. Show the exact process tool invocation to close the interactive session.
| Checked | Without skill | With skill |
|---|---|---|
| Sends Ctrl+C byte sequence \x03 with process action write or uses process action kill | Missed | Passed |
| Does not send /exit as command text to the interactive session | Missed | Passed |
The instructions your model reads when the skill loads.
Use OpenCode as an autonomous coding worker orchestrated by Hermes terminal/process tools. OpenCode is a provider-agnostic, open-source AI coding agent with a TUI and CLI.
npm i -g opencode-ai@latest or brew install anomalyco/tap/opencodeopencode auth login or set provider env vars (OPENROUTER_API_KEY, etc.)opencode auth list should show at least one providerpty=true for interactive TUI sessionsShell environments may resolve different OpenCode binaries. If behavior differs between your terminal and Hermes, check:
terminal(command="which -a opencode")
terminal(command="opencode --version")
If needed, pin an explicit binary path:
terminal(command="$HOME/.opencode/bin/opencode run '...'", workdir="~/project", pty=true)
Use opencode run for bounded, non-interactive tasks:
terminal(command="opencode run 'Add retry logic to API calls and update tests'", workdir="~/project")
test cases passed, vs 1 / 10 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.