Pin the current parent thread to a chosen AI model through Weave Router while subagents keep automatic model selection. An optional effort setting controls the model's reasoning effort.
Pin the current parent thread to a model through the Weave Router while subagents route automatically.
Review the instructions the agent will receive before you install.
When the user requests $force-parent <model-id>[:effort], run this skill's
scripts/emit.sh using the absolute path of this skill directory. Pass the
model and optional effort as one quoted argument. If no model was supplied,
ask which model to pin.
The script prints a leading-space /force-parent directive. The Weave Router
reads that exec output and pins only the invoking thread, then continues this
turn. Run it once, do not repeat its output as a user message, and report the
router's response. The directive requires a router version supporting
force-parent; do not claim success without its acknowledgment.
$force-parent replaces any conversation-wide $force-model pin. Children
keep their normal routing policy. $force-model restores conversation-wide
pinning; $unforce-model clears either mode. Model aliases and :effort
suffixes follow $force-model syntax. A compaction that changes the thread's
first user message changes its identity; reapply the pin in that thread.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Investigate unexpected Claude Code output by matching a session’s local transcript with production router logs. Identify the serving model and trace response conversion code to explain empty blocks, tool output, or other rendering symptoms.
Investigate a Codex CLI session by matching its local conversation record with production router logs. Use the session ID to examine missing reasoning summaries, routing markers, unexpected models, or unusual tool calls and trace relevant code paths.
Switch Codex from Weave Router back to its normal provider for future sessions. Keep the existing login and router configuration, receive the command result, and retain the option to turn routing on again later.
Pin the current Codex session to a chosen model through Weave Router. This short alias accepts a model ID, runs the included script, and reports the router’s response while allowing the current turn to continue.
Pin the current Codex session to a specific model through Weave Router by providing its model ID. The skill applies the pin, continues the same turn, and reports the router's response.
Set up language servers, programs that help tools understand source code, for Go, TypeScript, Python, and Rust. Check missing prerequisites, install them with approval, and verify the lsp tool against a real source file.