Optim-Agent
UserHuman-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer agent workflows.
Categories
Indexed Skills (6)
optim-plans
MUST USE when a user asks to plan, brainstorm, design, scope, review, or evaluate a repo change before implementation; do not use for direct implementation-only requests, factual/explanation questions, trivial operations, or explicit no-plan requests.
analyze-and-plan
MUST USE when investigating a bug, CI failure, test failure, regression, incident, broken behavior, root cause, RCA, or debug-why problem before deciding whether to create an optim-plans solution plan; do not use for ordinary feature ideas, vague product planning, direct implementation-only requests, factual/explanation questions, trivial operations, or explicit no-plan requests.
mini-plan
Use mini-plan for subtle low-risk repo changes needing one alignment question before execution; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
big-plan
Use big-plan for broad or risky repo changes needing codebase inspection, websearch, and deeper refinement; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
huge-plan
Use huge-plan for open-ended high-risk repo efforts needing websearch during brainstorming and refinement until convergence; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
plan
Use plan for normal repo changes needing bounded decisions, refinement, and high-priority review before execution; exclude direct implementation-only, factual/explanation, trivial, or explicit no-plan requests.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.