Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mdsakalu/agent-plugins/plugin install workspaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mdsakalu/agent-plugins/cd)<a href="https://agentmods.dev/commands/mdsakalu/agent-plugins/cd"><img src="https://agentmods.dev/badge/commands/mdsakalu/agent-plugins/cd/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/mdsakalu/agent-plugins/cd"><img src="https://agentmods.dev/badge/commands/mdsakalu/agent-plugins/cd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00013 | $0.00628 |
| Opus 5.5 | $0.00005 | $0.00251 |
| Sonnet 5.5 | $0.00003 | $0.00126 |
| Haiku 4.5 | $0.00001 | $0.00063 |
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 1mo 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.
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: $ARGUMENTS
Steps
- Read
~/.claude/workspace-config.jsonto get the metarepo path. Expand~to$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
--freshflag — 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 underrepos/<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:newor/workspace:list
- Build the target path:
<metarepo>/repos/<repo>/<workspace>/ - Determine the switch method:
- If
ZMX_SESSIONenv var exists (inside zmx): Run the respawn script:
Passbash ${CLAUDE_PLUGIN_ROOT}/scripts/workspaces/respawn-claude.sh <workspace-path> $PPID [--fresh]--freshif 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:
- Exit Claude or open a new session in that directory
- Run
cd <workspace-path>in their terminal Warn that Claude cannot change its working directory mid-session.
- If
- 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_SESSIONenv var before attempting respawn. $PPIDis Claude's PID needed by the respawn script.- Never run the respawn script outside of zmx.
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.
- 1mo ago First seen · 47 lines · 13 tokens per session scan A 9af558c54d7f
cd is a command published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 628 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.