Set up ac for your user, or upgrade an earlier setup: my-coding and my-language skills, the global CLAUDE.md and settings.json, each write gated.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# /ac:install
Tunes your user-scope environment so the ac workflow replaces the matching Claude Code built-ins. Safe defaults apply silently; anything that loosens a gate or touches a secret is opt-in.
Request: $ARGUMENTS
Precondition: the ac plugin is already installed and loaded. This command does not bootstrap the install and never calls `/plugin marketplace add` or `/plugin install`. It writes only under `~/.claude/`, and only the files each phase names; the one exception is the wrapper line 3d adds to a shell rc file, and only after the operator says yes.
## Phase 0: Identity, arguments, preflight, languages
You are the `/ac:install` orchestrator. You interview the operator, delegate skill authoring to `ac:skill-creator`, and write user-scope config behind explicit gates.
**CAN**: Use `Read`, `Write`, `Edit`, `Bash`, `AskUserQuestion`. Invoke `ac:skill-creator` through the `Skill` tool. Probe the ac MCP server with `mcp__plugin_ac_ac__resolve-library`. Write the `.proposed` sidecar, the `.bak-ac-install` backups, the `~/.claude/ac-install.json` answer record, and the stable rules copy at `~/.claude/ac/working-rules.md`.
…
The line at the top of this page pins the label git:20261031.691428e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_tijjxximd242ztku
GET https://markdownregistry.com/api/v1/resolve?ref=anilcancakir/claude-code/install
GET https://markdownregistry.com/api/v1/blob/7b8a68e669ee2c134de53264b26dca199ca3fd2787f54a841463af55a2a3f537
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
anilcancakir/claude-code · opencode/ac/skills/architecture-md-writer/SKILL.md · Write or audit an ARCHITECTURE.md for agents: boundaries, invariants with verify commands, flows and a change guide…
anilcancakir/claude-code · opencode/ac/skills/auto/SKILL.md · Away mode: carry the run in progress, or a new request, to completion unattended, ending at one verification gate. Use…
anilcancakir/claude-code · opencode/ac/skills/commit/SKILL.md · Split the working-tree changes into atomic commits, preflight and push them; also rebase, squash and trace history. Add…
anilcancakir/claude-code · opencode/ac/skills/coordinate/SKILL.md · Turn a large request into a reviewed roadmap of bundles and drive them through parallel ac/lane worktrees. Use when a…
anilcancakir/claude-code · opencode/ac/skills/design-md-writer/SKILL.md · Write or audit a visual-identity DESIGN.md: design tokens plus rationale in the Google Labs format, for UI agents. Use…
anilcancakir/claude-code · opencode/ac/skills/execute/SKILL.md · Run an approved ac plan to completion, wave by wave, with cost-tiered workers, per-wave verification and a final…
anilcancakir/claude-code · opencode/ac/skills/flow/SKILL.md · Run a medium or large request on the main thread: parallel research, interview, build in slices, oracle review. Use…
anilcancakir/claude-code · opencode/ac/skills/frontend-design/SKILL.md · Build distinctive, accessible web and mobile UI from a committed design direction and token plan. Use when building or…
anilcancakir/claude-code · opencode/ac/skills/github-cli/SKILL.md · Work with GitHub repositories, issues, PRs, releases and Actions runs through the gh CLI instead of web fetches. Use…
anilcancakir/claude-code · opencode/ac/skills/plan/SKILL.md · Plan a change: research in parallel, ask only the decisions the user must make, write a tiered plan. Writes no code…
anilcancakir/claude-code · opencode/ac/skills/product/SKILL.md · Turn an idea into a feasibility-checked PRD and a parallel-ready roadmap through research and an interview. Runs when…
anilcancakir/claude-code · opencode/ac/skills/project-md-writer/SKILL.md · Write or audit a PROJECT.md (what, scope, constraints, decisions) for agents; commands and conventions go in AGENTS.md…
smol-machines/smolvm · docs/install/SKILL.md · Installs smolvm from a published release and proves the host can actually boot a microVM before any other work starts…
jmagly/aiwg · agentic/code/addons/aiwg-utils/skills/install/SKILL.md · Install AIWG-compatible packages from remote Git repositories into the current workspace
tykimos/agent-native-agent · skills/install/SKILL.md · Install and run ANA (Agent-Native Agent) from scratch on macOS, Linux, or Windows (via WSL) — analyze the environment…
rossoctl/context-guru · context-guru-plugin/skills/install/SKILL.md · Install a local context-guru proxy and route this project's Claude Code sessions through it, so long sessions stop…
pierry/harness-kit · skills/install/SKILL.md · Install the harness-kit pipeline into the current project. Copies agents, slash commands, skills, and hooks into the…
terrylica/cc-skills · plugins/openwolf/skills/install/SKILL.md · Install openwolf npm and run `openwolf init` in cwd. TRIGGERS - install openwolf, openwolf init, set up openwolf.
