When the agent stops, a cheap model audits the whole conversation against ~/.agents/AGENTS.md. Rule violations are fed back to the agent on your next message.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin turn-check in dzianisv/opencode-plugins. Commands read from the repo's manifest — 12 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
python3 "${CLAUDE_PLUGIN_ROOT}/claude/stop.py"
python3 "${CLAUDE_PLUGIN_ROOT}/claude/prompt.py"
python3 "${CLAUDE_PLUGIN_ROOT}/claude/session_end.py"
End-of-session retrospective: finds scripts, CLI tools, fixes and corrections from the session and proposes the right home for each (new or edited skill, AGENTS.md/CLAUDE.md, memory, hook, command, subagent). Nothing is written without approval. Also ships an opencode plugin.
1 command · hooks
Injects a short-reply, plain-English instruction into every prompt so replies don't overwhelm. Also ships an opencode plugin.
hooks
Re-prompts Claude Code when it stops prematurely — catches PERMISSION-SEEKING, STOPPED-WITH-TODOS, and FALSE-COMPLETE failure modes (78% of real agent stops are premature), and injects targeted recovery instructions via the Stop hook.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.