Borrowing it
Nothing to install: this file belongs to runvendo/vendo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/runvendo/vendo/main/.claude/skills/workbench/SKILL.mdgit clone --depth 1 https://github.com/runvendo/vendoWrote 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/skills/runvendo/vendo/workbench)<a href="https://agentmods.dev/skills/runvendo/vendo/workbench"><img src="https://agentmods.dev/badge/skills/runvendo/vendo/workbench/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/skills/runvendo/vendo/workbench"><img src="https://agentmods.dev/badge/skills/runvendo/vendo/workbench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00486 |
| Opus 5.5 | $0.00000 | $0.00194 |
| Sonnet 5.5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
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 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.
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).
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 Changed b6cd5ae6ac30
- 1mo ago First seen · 48 lines · 0 tokens per session scan A f56535ad8b37
workbench is a skill published in the GitHub repository runvendo/vendo (633 stars, last pushed 11d 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.
Other skills, from other repositories
resolve-handoff
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
iterate-implementation
Only use when the user explicitly invokes this skill by name.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, resolve/search/record, graph workbench reads/writes, resource (document payload) commands, and pot scope behavior.