Agent skill · research science · aradotso
hitcc-claude-code-reverse-engineering
hitcc-claude-code-reverse-engineering — an agent skill for coding agents.
Why this skill is useful
Provides detailed analysis and documentation of the internal workings of Claude Code CLI, enabling users to build compatible alternatives or reference its architecture.
What it needs
About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash npm pack @anthropic-ai/claude-code@2.1.84 bash git clone https://github.com/hitmux/HitCC.git cd HitCC python recoverytools/ scripts — Python 3.x required Example: run a cleanup pass on unpacked CLI source python recoverytools/cleanup.py --input ./unpackedcli --output ./cleanedcli docs/ ├── 00-overview/ │ ├── 00-index.md ← Start here for global entry │ ├── 01-scope-and-evidence.md ← What is known vs. unknown │ └── 02-document-style-and-structure-conventions.md ├── 01-runtime/ │ ├── 01-product-cli-and-modes.md ← CLI shape, command tree, mode dispatch │ ├── 02-session-transcript-persistence.md │ ├── 03-input-compilation-and-agent-loop.md │ ├── 04-model-adapter-and-provider.md │ ├── 05-web-search-and-web-fetch.md │ ├── 06-telemetry-and-control-plane.md │ └── 07-settings-system.md ├── 02-execution/ │ ├── 01-tool-execution-core.md │ ├── 02-hook-runtime-and-permissions.md │ ├── 03-prompt-assembly-and-context.md │ └── 04-attachments-and-tool-use-context.md ├── 03-ecosystem/ │ ├── 01-resume-fork-sidechain-subagent.md │ ├── 02-remote-persistence-and-bridge.md │ ├── 03-mcp-integration.md │ ├── 04-skill-and-plugin.md │ └── 05-tui-runtime.md ├── 04-rewrite/ │ ├── 01-candidate-architecture.md │ └── 02-open-questions-and-judgment.md └── 05-appendix/ ├── glossary.md └── evidence-map.md User Input → Input Compilation Pipeline → Context assembly (system prompt + rules + attachments) → Tool definitions injection → LLM Request (streaming) → Stream handler collects tooluse blocks → Tool Execution Core → Concurrent execution with permission checks → Hook runtime (pre/post hooks) → Result injection → next loop iteration → Compact branch (context window management) python Conceptual rewrite pattern based on HitCC docs/02-execution/01-tool-execution-core.md import asyncio from typing import Any async def executetoolsconcurrent( toolcalls: list[dict], permissionchecker, hookrunner, ) -> list[dict]: """ Mirrors Claude Code's concurrent tool dispatch with permission gating. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/hitcc-claude-code-reverse-engineering