adr
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as…
Install plugin runner scripts into project .claude/scripts/ for persistent use without plugin loaded
Claude Code
$ npx -y skills add sd0xdev/sd0x-harness --skill install-scripts --agent claude-code
Codex
$ npx skills add sd0xdev/sd0x-harness --skill install-scripts -a codex -y
Cursor
$ npx skills add sd0xdev/sd0x-harness --skill install-scripts -a cursor -y
Gemini CLI
$ npx skills add sd0xdev/sd0x-harness --skill install-scripts -a gemini-cli -y
GitHub Copilot
$ npx skills add sd0xdev/sd0x-harness --skill install-scripts -a github-copilot -y
OpenCode
$ npx skills add sd0xdev/sd0x-harness --skill install-scripts -a opencode -y
Windsurf
$ npx skills add sd0xdev/sd0x-harness --skill install-scripts -a windsurf -y
name: install-scripts description: "Install plugin runner scripts into project .claude/scripts/ for persistent use without plugin loaded" allowed-tools: Read, Glob, Write, AskUserQuestion, Bash(mkdir:*), Bash(diff:*), Bash(git:*), Bash(ls:*), Bash(chmod:*), Bash(cp:*), Bash(node:*)
Phase 0: Resolve mode; obsolete-set migration (first for non-list invocations; --dry-run forwarded) Phase 1: Locate plugin scripts dir Phase 2: Enumerate scripts (core + skill scripts) Phase 3: Determine install set (--all, --skill, specific names) Phase 4: Copy scripts + dependencies to .claude/scripts/ Phase 4.5: Update manifest Phase 5: Output report
Same shared migration `/install-hooks` runs, invoked here too so **neither entry point can reproduce the unsafe order by hand** (hook-lightweighting § 3.6). **Resolve the invocation mode first**: a listing invocation skips this phase (read-only), and `--dry-run` is forwarded so the migration also only reports:
# --dry-run → append --dry-run to the command below; list-only invocations skip Phase 0
node "${CLAUDE_PLUGIN_ROOT}/scripts/migrate-hook-lightweighting.js" --repo "$(git rev-parse --show-toplevel)"It deregisters obsolete settings entries first and deletes the retired enforcement-layer files only after the settings writes succeed. On exit 1, stop the install and surface the report. Include the migration's report lines in Phase 5's output.
$ARGUMENTS
| Argument | Description | |----------|-------------| | `--all` | Install all available core scripts | | `--list` | List available core scripts without installing | | `--dry-run` | Show what would be installed, no changes | | `--force` | Overwrite existing scripts with different content | | `--skill <name>` | Install all scripts from the specified skill | | `--skill-all` | Install scripts from all skills | | `--skill-list` | List all available skill scripts | | `script-names...` | Specific scripts to install |
| Type | Source | Target | |------|--------|--------| | Core scripts | `scripts/*.js`, `scripts/*.sh` | `.claude/scripts/` | | Core lib | `scripts/lib/*.js` | `.claude/scripts/lib/` | | Skill scripts | `skills/<name>/scripts/*` | `.claude/scripts/` |
| Scenario | Action | |----------|--------| | Target missing | Copy | | Target identical | Skip (up to date) | | Target differs | Skip + warn (use --force to overwrite) |
## Install Scripts Report | Script | Type | Status | |--------|------|--------| | precommit-runner.js | core | installed | | lib/utils.js | core-lib | up to date | | git-profile.sh | skill | installed | Installed: N | Skipped: M | Conflicts: K
Language: English | 繁體中文 | 简体中文 | 日本語 | 한국어 | Español The harness layer for Claude Code. Let the model choose the path. Keep "done" verifiable. Claude has discretion inside a closed, test-pinned anchor set.
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as…
Install and set up the optional agentctl mod (task scope, refusal before execution, evidence that goes stale, model-free…
Architecture design and documentation. Produces 3-architecture.md with component diagrams, data flow, integration points, and…
Context-aware Q&A with auto context gathering. Use when: user has a quick question about codebase, git history, rules, docs, or…
Industry best practices conformance audit with mandatory adversarial debate. Produces audit artifact: verdict (OK/WARN/FAIL) +…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.