cd-enter

A command that shows the instructions for a Conductor branch and explains how to open it in a separate coding session. A branch is an isolated line of project work.

In plain words
What is it for?
Use it to start work on a named branch, bind a new session to that branch, and learn the steps for finishing and merging it.
Why use it?
It keeps branch work separate from the main session and explains how to complete and later merge approved changes.

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/jinghao67/conductor/cd-enter
Clone the repo
git clone --depth 1 https://github.com/Jinghao67/conductor
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 274 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 $0.00015 $0.00274
Opus 5 $0.00008 $0.00137
Sonnet 5 $0.00003 $0.00055
Haiku 4.5 $0.00002 $0.00027

Measured 2d ago against content hash 457da779e4b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cd-enter 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.

claude-code/commands/cd-enter.md · 19 lines

What it actually says

Brief for $ARGUMENTS (this is exactly what the branch session will receive): !cat ".conductor/branches/$ARGUMENTS/brief.md" 2>/dev/null || echo "No brief for $ARGUMENTS — run /cd-branch first."

To start this branch as a separate session you drive directly (this keeps the master clean — the master never sees this branch's working history, only its final completion report):

  1. Open a new terminal tab/window in this project directory and run claude.
  2. In that new session, run: /cd-bind $ARGUMENTS
    • This binds the session to $ARGUMENTS; its SessionStart will then inject only the brief above, and the read-firewall will not apply (a branch is allowed to be dirty).
  3. Do the work there, interacting directly. When the user confirms it's done, run /cd-complete in that session.
  4. Back here in the master, run /cd-merge $ARGUMENTS to fold only the approved result in.

(Do not try to do the branch's work here in the master session.)

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 · 19 lines · 15 tokens per session scan A 457da779e4b9

Subscribe to this mod's changes

cd-enter is a command published in the GitHub repository Jinghao67/conductor (106 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 274 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 2026-08-30.