lollipopkit

lollipopkit/cc-plugins

Plugin Claude Code

Plugin marketplace listing 3 plugins: recursive-reasoning, devloop, context-firewall.

lollipopkit/cc-plugins

Instructions file

Instructions for lollipopkit/cc-plugins, covering claude.md, development commands, plugin management, linting & formatting and architecture & code structure.

lollipopkit/cc-plugins

Plugin Claude Code

Context Firewall: use sub-agents to preprocess large inputs with evidence contracts and low-cost verification.

lollipopkit/cc-plugins

Agent

Use this agent when multiple FileWorker results need to be merged into a single SubResult.v1, with de-duplication, clustering, and conflict detection.

lollipopkit/cc-plugins

Agent

Use this agent when a high-risk TaskSpec/SubResult needs an independent second pass to reduce hallucinations, validate coverage, or resolve cross-file causal claims.

lollipopkit/cc-plugins

Agent

Use this agent when a task requires reading or scanning large inputs (files/logs/PDFs/images/tool outputs) and returning a compressed, auditable SubResult fragment with evidence locators.

lollipopkit/cc-plugins

Command

Run the context-firewall workflow: split inputs, invoke FileWorkers, aggregate into SubResult.v1.

lollipopkit/cc-plugins

Command

Generate a TaskSpec.v1 JSON template for the context-firewall workflow.

lollipopkit/cc-plugins

Command

Verify SubResult.v1 by sampling evidence locators and re-reading only referenced snippets.

lollipopkit/cc-plugins

Skill Claude CodeCodex

This skill should be used when the user asks to "analyze a large log", "summarize a big file", "read the whole repository", "process long tool output", "avoid context window overflow", "use sub-agents for preprocessing", "add evidence with line numbers", "verify claims with locators", or mentions "TaskSpec"…

lollipopkit/cc-plugins

Plugin Claude Code

Iterate until ready to merge: create branch, fix, commit, open PR, wait for AI review, apply feedback, repeat.

lollipopkit/cc-plugins

Command

A command that runs a repeating software-development workflow from a code change through a pull request and review.

lollipopkit/cc-plugins

Skill Claude CodeCodex

An iterative engineering workflow for fixing an issue, running tests, opening a pull request, and responding to code-review comments until the work is ready to merge.

lollipopkit/cc-plugins

Plugin Claude Code

Recursive Reasoning Engine - iteratively refine answers through multi-pass reasoning using Self-Refine, Reflexion, Tree of Thoughts, and multi-model collaboration.

lollipopkit/cc-plugins

Agent

Debugs multi-model/recursive-arena failures by checking .env discovery, ARENA variables, provider base URLs, and common misconfigurations. Use proactively when multi-model scripts fail or when user asks to configure multi-model.

lollipopkit/cc-plugins

Agent

Specialized executor for recursive reasoning sub-tasks. It performs specific execution steps (coding, analysis, research) as directed by the Master agent.

lollipopkit/cc-plugins

Command

Run multi-model battle for iterative refinement across LLMs.

lollipopkit/cc-plugins

Command

Combine recursive refinement with multi-model battles.

lollipopkit/cc-plugins

Command

Master orchestrator for iterative multi-pass reasoning using Sub-Agents.

lollipopkit/cc-plugins

Skill Claude CodeCodex

Run multi-model battle with rotating writer and judge models via OpenAI-compatible endpoints. Use when users ask to battle or compare models, run multi-LLM critique, or iteratively improve an answer across models.

lollipopkit/cc-plugins

Skill Claude CodeCodex

Combine recursive outer-loop refinement with multi-model arena generation each round. Use when users request recursive arena, multi-LLM consensus with iterative refinement, or recursive plus model-battle workflows.

lollipopkit/cc-plugins

Skill Claude CodeCodex

Recursive master-orchestration for complex multi-step tasks. Decompose work, delegate execution to sub-agents, and iterate until verified. Use when users request recursive reasoning, multi-pass refinement, or explicit plan-execute-verify loops.

lollipopkit/agent-skills

Skill Claude CodeCodex

Clean Codex local history artifacts that can contain logs, prompts, user input text, command traces, and session transcripts while preserving memories and configuration. Use when the user asks to delete, purge, wipe, prune, reset, or preview Codex history/log/session/input records, especially /.codex/history.jsonl…

lollipopkit/agent-skills

Skill Claude CodeCodex

Create concise, evidence-based handoff notes for another AI coding agent. Use when the user asks for a handoff, continuity note, next-agent summary, progress transfer, "告诉别的 agent", "handoff skill", "交接", or wants the current state, completed work, remaining plan items, risks, and next steps captured for another agent…