workbench

workbench is a skill for Claude Code, Codex from runvendo/vendo. It costs 0 tokens per session (486 once invoked), scanned A, original, Apache-2.0.

A live development workbench for inspecting and debugging the vendo() harness or screen agent. A harness is the code that runs and monitors an agent's steps, context, tools, and safety checks.

In plain words
What is it for?
Use it to run a local demo, inspect timelines, context, tools, guards, and raw data, replay a canned turn, and test edits with hot reload.
Why use it?
It makes internal agent behaviour visible while you edit the code, so you can see what happened during a turn and investigate problems faster.

Skill for Claude CodeCodex

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 skills/runvendo/vendo/workbench
Any agent
npx skills add runvendo/vendo --skill workbench
Clone the repo
git clone --depth 1 https://github.com/runvendo/vendo

Made for: Claude Code, Codex.

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 workbench

README.md
[![agentmods](https://agentmods.dev/badge/skills/runvendo/vendo/workbench.svg)](https://agentmods.dev/skills/runvendo/vendo/workbench)
Your own site
<a href="https://agentmods.dev/skills/runvendo/vendo/workbench"><img src="https://agentmods.dev/badge/skills/runvendo/vendo/workbench.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 486 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 $0.00000 $0.00486
Opus 5 $0.00000 $0.00243
Sonnet 5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00049

Measured today against content hash b6cd5ae6ac30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workbench 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 today.

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/skills/workbench/SKILL.md · 48 lines

What it actually says

workbench

Maple (examples/demo-bank) plus whole-graph dev source aliasing plus a dev-only internals pane behind VENDO_WORKBENCH=1 (server env; unset means zero diagnostic parts on the wire). Shipped in PR #1130.

Run

pnpm install && pnpm build       # once — dist must exist; @vendoai/vendo/store stays dist-pinned, so edits there need a rebuild
VENDO_WORKBENCH=1 pnpm --filter demo-bank dev
open http://localhost:3000

Pane docks right: Timeline / Context / Tools / Guard / Raw, plus a turn selector.

Loop

Chat → read the pane → edit packages/*/src (loop.ts, compaction.ts, vendo.ts are the usual suspects — note packages/vendo/src/harnesses/vendo/ is an author-involved zone per its CLAUDE.md) → save → the next message runs the edit. In-flight turns finish on the old code.

Levers

  • MAPLE_HARNESS=context-e2e — 32k context window, so a few messages reach compaction.
  • Ask Maple to build something to watch a screen-agent run (tagged, 10-step cap).
  • The "demo feed" button replays a canned turn for pane-UI work without spending tokens.

Architecture, three lines

Harness sink packages/vendo/src/harnesses/workbench.ts → transient data-vendo-debug parts (never persisted) → ui feed store packages/vendo/src/ui/chrome/workbench-store.ts (20-turn retention) → pane in examples/demo-bank/src/components/vendo/workbench/.

Measuring

After a harness change, pnpm build, then the genbench skill for before/after scores (genbench reads built dists).

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. today Changed b6cd5ae6ac30
  2. 4d ago First seen · 48 lines · 0 tokens per session scan A f56535ad8b37

Subscribe to this mod's changes

workbench is a skill published in the GitHub repository runvendo/vendo (601 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 486 tokens. 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.

Related

Other skills, from other repositories

memory

Use durable BB memory when prior project knowledge or cross-project user preferences can improve the current task, and save durable new learning through the bb memory CLI.

get-bb/bb · 32 tokens

workflows

Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.

get-bb/bb · 47 tokens

submit-a-plugin

Submit a bb plugin to the BB Community marketplace. Use whenever a user asks to submit, list, publish, or add a plugin to the BB marketplace, or asks for a marketplace pull request. This skill validates the plugin and release, creates the marketplace entry and icon, and opens the pull request.

get-bb/bb · 64 tokens

secrets

Securely request API keys, access tokens, passwords, webhook secrets, or other credentials and write them to a dotenv file without exposing their values to the agent. Use whenever a task needs a credential that the user must supply.

get-bb/bb · 48 tokens

analyze-bundle

Convert Next.js bundle analyzer data to NDJSON and explore it.

vercel-labs/dev3000 · 17 tokens

regex-mastery

Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.

alibaba/anolisa · 60 tokens