install

An interactive setup command for the ac plugin, which is already installed in Claude Code.

In plain words
What is it for?
It checks the computer and existing configuration, asks setup questions, creates personal skills, updates global instructions, and configures settings when approved.
Why use it?
It removes the need to manually configure personal coding preferences, language guidance, global instructions, and selected Claude Code settings.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/anilcancakir/claude-code/install
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code
Per session 293 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,991 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00293 $0.06991
Opus 5 $0.00147 $0.03495
Sonnet 5 $0.00059 $0.01398
Haiku 4.5 $0.00029 $0.00699

Measured 2d ago against content hash ca7601b27999, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

install scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Interactive setup for a machine that already has the ac plugin installed. This command tunes your user-scope environment: it generates your personal `my-coding` and `my-language` skills, merges the workflow-discipline se

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Workflow discipline (operating mode, code-lookup ladder, investigation, verification, delegation, web tools) lives in the global CLAUDE.md section this command merges, not in a skill. CLAUDE.md reaches every main-threa
plugins/ac/commands/install.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ac:install

Interactive setup for a machine that already has the ac plugin installed. This command tunes your user-scope environment: it generates your personal my-coding and my-language skills, merges the workflow-discipline section into your global ~/.claude/CLAUDE.md, and configures ~/.claude/settings.json so the ac workflow replaces the matching Claude Code built-ins. Safe defaults apply silently; security-sensitive keys and your MCP token are opt-in and never rendered in plaintext.

Request: $ARGUMENTS

Precondition: the ac plugin is already installed and loaded (you are running this as /ac:install). This command does not bootstrap the install. It never calls /plugin marketplace add or /plugin install. It writes only under ~/.claude/ and only the files each phase names.

Phase 0: Identity, Arguments, and Preflight

You are the /ac:install orchestrator. You interview the user, delegate skill creation to ac:skill-creator, and write user-scope config files behind explicit gates.

CAN: Use Read, Write, Edit, Bash, AskUserQuestion. Invoke ac:skill-creator via the Skill tool (Phases 1 and 2). Probe the ac MCP server by calling mcp__plugin_ac_ac__resolve-library. Write a ~/.claude/CLAUDE.md.proposed sidecar and a ~/.claude/settings.json.bak-ac-install backup.

CANNOT: Hand-write my-coding or my-language SKILL.md content; that is ac:skill-creator's job. Blind-overwrite ~/.claude/CLAUDE.md or ~/.claude/settings.json; both go through merge plus a gate or a backup. Run /plugin marketplace add or /plugin install. Edit files outside ~/.claude/. Write an allow rule broader than the literal server segment (mcp__plugin_ac_ac__*, never mcp__*).

MUST: Honor every flag from 0a for the rest of the run. Under --dry-run, render every planned change but call no Write or Edit. Back up ~/.claude/settings.json before the Phase 4 merge. Skip a skill that already exists unless the user chooses Recreate. Keep the merged global CLAUDE.md within the 200-line guidance; the Phase 3 fenced block is roughly 85 lines, so trim the operator's own content rather than the discipline sections if the total would overflow.

Read the full file on GitHub · 380 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 380 lines · 0 tokens per session scan D ca7601b27999

Subscribe to this mod's changes

install is a command published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed 13d ago), licensed MIT. It adds 293 tokens to every session and 6,991 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.