ShaftHQ

ShaftHQ/SHAFT_ENGINE

Skill Claude CodeCodex

Load the canonical ChaosEngine policy and this repository's selected project profile before every task.

ShaftHQ/SHAFT_ENGINE

Skill Claude CodeCodex

Optional local coding loop as a mechanical or default delegate. Use when the decider model wants a cheap local coder and a hardware probe says the host can run one.

ShaftHQ/SHAFT_ENGINE

Skill Claude CodeCodex

Use when opening or rewriting a work item on any git-based SCM. Source-control agnostic; GitHub, GitLab, and Azure Boards are adapters only.

ShaftHQ/SHAFT_ENGINE

Plugin Claude Code

Official ShaftHQ marketplace. Agent skills that teach AI coding agents to write, record, and debug SHAFTENGINE tests correctly.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Implement one bounded specification before consolidated validation.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Perform deterministic reversible spec-exact work; stop on ambiguity.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Own planning, architecture, synthesis, and final verification.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Perform an independent read-only adversarial review; never edit.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Reproduce behavior and produce regression and acceptance evidence.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Use for main-thread orchestration covering decomposition, architecture, synthesis, and final verification.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Use for a bounded implementation spec; runs at the default capability level and may assign only mechanical slices downward.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Use for deterministic, reversible, spec-exact work only.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Use for read-only review of spec compliance, quality, and verification gaps, including the independent adversarial pass.

ShaftHQ/SHAFT_ENGINE

Agent Claude Code

Use for reproduction, regression proof, and affected-flow acceptance evidence.

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs after a tool call finishes for Bash, PowerShell, shell_command, exec_command, functions[.]exec, run_shell_command, run_in_terminal, Write, Edit, NotebookEdit, apply_patch, write_file, create_file, edit_file, replace, replace_string_in_file, multi_replace_string_in_file, mcp__[^, ]*memory__(?:remember_memory…

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs when a tool call fails for Bash, PowerShell, shell_command, exec_command, functions[.]exec, run_shell_command, run_in_terminal, Write, Edit, NotebookEdit, apply_patch, write_file, create_file, edit_file, replace, replace_string_in_file, multi_replace_string_in_file, mcp__[^, ]*memory__(?:remember_memory…

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs before the context is compacted, executing guard.py via python3. From ShaftHQ/SHAFT_ENGINE.

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs before the agent uses a tool for Task, Agent, spawn_agent, collaboration[.]spawn_agent, task, agent, Bash, PowerShell, shell_command, exec_command, functions[.]exec, run_shell_command, run_in_terminal, Write, Edit, NotebookEdit, apply_patch, write_file, create_file, edit_file, replace, replace_string_in_file…

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs when a session ends, executing guard.py via python3. From ShaftHQ/SHAFT_ENGINE.

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs when a session starts, executing guard.py via python3. From ShaftHQ/SHAFT_ENGINE.

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs when the agent finishes a response, executing guard.py via python3. From ShaftHQ/SHAFT_ENGINE.

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs when a subagent finishes, executing guard.py via python3. From ShaftHQ/SHAFT_ENGINE.

ShaftHQ/SHAFT_ENGINE

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing guard.py via python3. From ShaftHQ/SHAFT_ENGINE.

ShaftHQ/SHAFT_ENGINE

Settings file Claude Code

Agent settings declaring 9 hook events (PostToolUse, PostToolUseFailure, PreCompact, PreToolUse) and 18 allowed tools.