agentmods.dev

link

A guided setup command for connecting the toolkit to either a VB Studio project or a standalone VBCS application.

In plain words
What is it for?
It is for selecting a project or application, locating or cloning its checkout, and setting the toolkit's default connection.
Why use it?
It helps configure the correct local repository or application connection before other toolkit commands are used.

Command for Claude Code

0 20d ago A scan 16 tokens original MIT
View the source file vanamthrishul/ovb3-bridge
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/vanamthrishul/ovb3-bridge/link
Clone the repo
git clone --depth 1 https://github.com/vanamthrishul/ovb3-bridge

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 713 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 $0.00016 $0.00713
Opus 5 $0.00008 $0.00357
Sonnet 5 $0.00003 $0.00143
Haiku 4.5 $0.00002 $0.00071

Measured yesterday against content hash 8ee4c2d31384, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

link 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.

.claude/commands/link.md · 25 lines

What it actually says

Guide the user through linking either a VB Studio (VBS) project or a standalone VBCS instance, so the rest of the toolkit knows what to work against. Ask, don't assume:

  1. Ask whether they're linking a VB Studio project (git-backed — pages/flows/chains live as files in a git repo) or a standalone VBCS instance (REST-only, no git remote for the app).

  2. If VB Studio:

    • Ask whether they already have a local checkout, or need one cloned.
    • Already checked out: ask for its absolute path. Read .env's current VBS_WORKSPACE_DIR. If the checkout's parent directory matches it, nothing to do — just confirm with list_repos. Otherwise, use Edit to set VBS_WORKSPACE_DIR in .env to the checkout's parent directory (or VBCS_REPO_PATH directly to the checkout itself, for a single-repo setup), then confirm with list_repos.
    • Needs cloning: ask for the git remote URL and a short destination folder name, then call git_clone (mcp__vbcs__git_clone) with those. Report the resulting path.
    • If the repo hosts more than one app (check via list_apps after cloning/pointing), ask which one is the default and set VBCS_APP_NAME in .env via Edit.
    • Tell the user their VB Studio git credentials (VBSTUDIO_GIT_USERNAME/VBSTUDIO_GIT_TOKEN in .env) must already be filled in for git_clone/git_pull/git_push to work, and that filling those in is on them, never in this conversation.

  3. If standalone VBCS:

    • Ask for the instance's base URL only (not a secret). Use Edit to set VBCS_BASE_URL in .env to that value.
    • Explicitly tell the user: their IDCS username and password must be filled into VBCS_IDCS_USERNAME / VBCS_IDCS_PASSWORD in .env by them, directly — never paste credentials into this conversation.
    • Explain that a session restart is required afterward (env vars load once at server startup), and that once restarted, /vbcs-list-apps (or vbcs_list_applications) can be used to verify the connection.
    • Do not attempt to call vbcs_list_applications yet if the credentials were just requested — it will fail until the user has filled them in and restarted.

  4. Only ever use Edit to write non-secret fields (VBS_WORKSPACE_DIR, VBCS_REPO_PATH, VBCS_APP_NAME, VBCS_BASE_URL). Never write, ask for, or echo back any credential/secret field — those are always the user's to fill in directly in .env.

  5. Finish with a short summary of what's now configured and what (if anything) the user still needs to fill in themselves before it's fully working.

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. yesterday First seen · 25 lines · 16 tokens per session scan A 8ee4c2d31384

Subscribe to this mod's changes

link is a command published in the GitHub repository vanamthrishul/ovb3-bridge (0 stars, last pushed 20d ago), licensed MIT. It adds 16 tokens to every session and 713 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.

E-commerceLanguagesclaudeclaude-codeclimcpmcp-serveroracle
Related

Other commands, from other repositories

speckit.tasks

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

Weaverse/weaverse · 18 tokens

dev

Runs Vendure in development mode. By default it starts three processes: the GraphQL server (ts-node ./src/index.ts), the worker (ts-node ./src/index-worker.ts), and the dashboard (a Vite dev server).

vendurehq/vendure · 0 tokens

start

Runs a project that has already been compiled with vendure build.

vendurehq/vendure · 0 tokens

pipeline-undo

Undo a pipeline run's result. With worktree isolation (the current engine), this is clean and low-risk: a run never touches your checkout — its result lives only on a pipeline/ branch (and, for a --push run, on the remote). "Undo" therefore means deleting that branch and its worktree, not reverting your working tree.

TheAstrelo/Claude-Pipeline · 0 tokens

rank-vertical

E-Commerce and Local Business SEO checks with auto-detection.

Houseofmvps/claude-rank · 16 tokens

create_worktree

description: Create worktree and launch implementation session for a plan.

humanlayer/humanlayer · 0 tokens