cc-init

A project setup command from Conductor that detects the current codebase, identifies its tools and commands, and initializes or updates the project instructions.

In plain words
What is it for?
Use it when starting a new project or bringing an existing one back into sync, so build, test, lint, formatting, and setup commands are recorded.
Why use it?
It reduces manual setup work and fills missing project details while preserving existing non-placeholder instructions in CLAUDE.md.

Command for Claude Code

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/yeisonrestrepo/code-conductor/cc-init
Clone the repo
git clone --depth 1 https://github.com/yeisonrestrepo/code-conductor

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00011 $0.00865
Opus 5 $0.00005 $0.00432
Sonnet 5 $0.00002 $0.00173
Haiku 4.5 $0.00001 $0.00086

Measured 2d ago against content hash 481b332fa664, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-init scanned grade A with 0 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

project-template/.claude/commands/cc-init.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 1 — Detect project state

List files in the project (exclude .git/, .claude/, node_modules/, and dot-files, max depth 3). Count source files found.

If the count is 0 or only CLAUDE.md / config files exist, treat this as a new/empty project (IS_NEW=true). Otherwise set IS_NEW=false.

Step 2 — Auto-detect and collect project identity

Check if scripts/detect-stack.mjs exists in the project root. If it does, run:

node scripts/detect-stack.mjs "$PWD"

Environment flags: CC_GLOB_DEPTH and any other CC_* env vars the user may have set are automatically inherited by the child node process — no explicit export or forwarding is required. The /cc-init command must NOT reset or unset these variables before calling detect-stack.

Capture the JSON output. For each field in the JSON (name, description, stack, build, test, lint, format, setup), check the corresponding line in CLAUDE.md:

  • If the CLAUDE.md line contains <command> (any case) or is blank after Key: → replace with the detected value using a single Edit call.
  • If the CLAUDE.md line already has a non-placeholder value → skip (never overwrite).

Apply all replacements in a single Edit call after collecting all detected values.

If scripts/detect-stack.mjs is missing or returns {}, skip auto-detection.

After auto-detection (or if skipped), check which identity fields remain blank:

Read CLAUDE.md. Check the ## Project Identity section.

If Name is still empty, ask the user all of these questions at once (not one at a time):

  1. What is the project name?
  2. One sentence: what does it do?
  3. Primary tech stack (e.g. "TypeScript + React", "Python + FastAPI") — only ask if IS_NEW=false AND stack was not auto-detected
  4. Response language preference? (default: en — only ask if context suggests otherwise)

If Name was already filled (by auto-detection or previous run), skip directly to Step 3 without asking.

Once any manual fields are collected, update CLAUDE.md with a single Edit call covering all remaining blank fields.

Read the full file on GitHub · 85 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 · 85 lines · 11 tokens per session scan A 481b332fa664

Subscribe to this mod's changes

cc-init is a command published in the GitHub repository yeisonrestrepo/code-conductor (6 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 865 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.