A workspace navigation command that moves into a selected repository workspace and can start a fresh Claude session when requested.

Use it with a repository/workspace path, a workspace name, or a partial name to switch directories, choose among matches, resume context, or start fresh.

It avoids manually locating workspace folders and can resolve exact, partial, or ambiguous names across repositories.

cd — Command by mdsakalu

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/mdsakalu/agent-plugins/cd

Clone the repo

git clone --depth 1 https://github.com/mdsakalu/agent-plugins

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 628 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00628
Opus 5	$0.00006	$0.00314
Sonnet 5	$0.00003	$0.00126
Haiku 4.5	$0.00001	$0.00063

Measured yesterday against content hash 9af558c54d7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cd 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 yesterday.

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.

workspace/commands/cd.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Switch to a workspace directory (with zmx respawn support).

Resolve the metarepo path by reading ~/.claude/workspace-config.json and expanding ~ to $HOME.

The user's request: $ARGUMENTS

Steps

Read ~/.claude/workspace-config.json to get the metarepo path. Expand ~ to $HOME.
Parse the user's input. Accept:
- <repo>/<workspace> — explicit: e.g., my-repo/epic-foo
- <workspace> — search all repos for a match; if ambiguous, ask user
- Partial/fuzzy name — search for matches and present options
- --fresh flag — start a fresh Claude session instead of resuming context
Scan <metarepo>/repos/*/ directories to discover repos. For each repo, check if a matching workspace directory exists under repos/<repo>/<workspace>/.
If no exact match found:
- Search across all repos for partial matches
- If multiple matches, present options via AskUserQuestion
- If no matches, suggest /workspace:new or /workspace:list
Build the target path: <metarepo>/repos/<repo>/<workspace>/
Determine the switch method:
- If ZMX_SESSION env var exists (inside zmx): Run the respawn script:
```
bash ${CLAUDE_PLUGIN_ROOT}/scripts/workspaces/respawn-claude.sh <workspace-path> $PPID [--fresh]
```
  Pass --fresh if the user requested a fresh session. Warn the user that Claude will restart. If --fresh, note it will be a brand new session. Otherwise, note the session will resume.
- If NOT in zmx: Show the workspace path and instruct the user to:
  1. Exit Claude or open a new session in that directory
  2. Run cd <workspace-path> in their terminal Warn that Claude cannot change its working directory mid-session.
Show the workspace path for reference.

Important

Always resolve metarepo from ~/.claude/workspace-config.json, never hardcode paths.
Workspaces live at <metarepo>/repos/<repo>/<workspace>/.
Handle ambiguous names gracefully — if a workspace name exists in multiple repos, ask which one.
The respawn script requires zmx. Check for ZMX_SESSION env var before attempting respawn.
$PPID is Claude's PID needed by the respawn script.
Never run the respawn script outside of zmx.

Read the full file on GitHub · 47 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.

yesterday First seen · 47 lines · 13 tokens per session scan A 9af558c54d7f

Subscribe to this mod's changes

cd is a command published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 628 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.

cd

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Steps

Important

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement