add-repo

add-repo is a command for Claude Code from mdsakalu/agent-plugins. It costs 10 tokens per session (540 once invoked), scanned A, original, MIT.

A repository-onboarding command that adds a GitHub repository to a shared metarepo, a central collection that tracks multiple repositories and their workspaces.

In plain words
What is it for?
Use it with a GitHub URL, an organization/repository name, or an organization name to clone and initialize a repository, record its metadata, and create its initial workspace notes.
Why use it?
It prepares the repository and its metadata in one workflow, reducing the setup needed before creating and managing workspaces.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the workspace plugin — 13 commands, 3 hooks shipped together

Good fit Use it with a GitHub URL, an organization/repository name, or an organization…

Compare 6 commands from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add mdsakalu/agent-plugins
Claude Code
/plugin install workspace

Made for: Claude Code.

Or install workspace, the plugin that ships this one along with the rest of its 13 commands, 3 hooks.

Wrote 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.

agentmods badge for add-repo

README.md
[![agentmods](https://agentmods.dev/badge/commands/mdsakalu/agent-plugins/add-repo.svg)](https://agentmods.dev/commands/mdsakalu/agent-plugins/add-repo)
Your own site
<a href="https://agentmods.dev/commands/mdsakalu/agent-plugins/add-repo"><img src="https://agentmods.dev/badge/commands/mdsakalu/agent-plugins/add-repo.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00010 $0.00540
Opus 5 $0.00005 $0.00270
Sonnet 5 $0.00002 $0.00108
Haiku 4.5 $0.00001 $0.00054

Measured 6d ago against content hash 5578c1183661, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

add-repo 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 6d 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.

workspace/commands/add-repo.md · 43 lines

What it actually says

Onboard a new repository into the universal metarepo.

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

The user's request: $ARGUMENTS

Steps

  1. Read ~/.claude/workspace-config.json to get the metarepo path. Expand ~ to $HOME.
  2. Parse the user's input for the repository source:
    • Full GitHub URL: https://github.com/org/repo
    • Shorthand: org/repo (e.g., acme/my-project)
    • Just an org name: use gh repo list <org> --limit 20 --json name,url to discover repos and let user pick
  3. Check if the repo is already onboarded:
    • Look for <metarepo>/repos/<name>/.repo.json
    • If found, inform the user and suggest /workspace:new instead
  4. Run the add-repo script:
    bash ${CLAUDE_PLUGIN_ROOT}/scripts/workspaces/add-repo.sh <url-or-org/repo>
    
    The script handles: cloning, JJ init, .repo.json, trunk workspace.json, symlinks, .git/info/exclude.
  5. Commit the new notes to the metarepo:
    cd <metarepo> && git add notes/<repo>/ && git commit -m "Onboard <repo> repository"
    
  6. Report success and suggest next steps:
    • /workspace:new <repo> <name> to create first workspace
    • /workspace:list to see all workspaces

Important

  • Always resolve metarepo from ~/.claude/workspace-config.json, never hardcode paths.
  • This clones a potentially large repository. Warn the user it may take a while.
  • Repos are cloned to <metarepo>/repos/<name>/trunk/ (gitignored).
  • Notes/metadata go to <metarepo>/notes/<name>/trunk/ (git-tracked).
  • Handle errors: auth failures, non-existent repos, network issues.
  • If gh is not authenticated, suggest gh auth login.
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. 6d ago First seen · 43 lines · 10 tokens per session scan A 5578c1183661

Subscribe to this mod's changes

add-repo is a command published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 540 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.