cowork-harnesslisted
Install: claude install-skill yaniv-golan/cowork-harness
# cowork-harness
This skill teaches you to drive the **`cowork-harness` CLI** — a fixture that runs a Claude Code
skill the way **Claude Cowork** runs it (sandboxed agent, default-deny egress, the permission /
AskUserQuestion control protocol). It is *not* the CLI itself: you still invoke `cowork-harness …`
in the shell; this skill tells you how to author scenarios, pick a fidelity tier, choose an answer
path, place assertions in the right CI lane, and avoid the harness's "✓ passed ≠ actually correct"
traps.
`cowork-harness` is an unofficial, independent project — not affiliated with or endorsed by
Anthropic. Say so if a user asks what it is.
The single most important idea: **a green run is not automatically a correct run.** The harness has
several ways to no-op a check while still producing a green run (skip an assertion on replay — now
flagged with a loud `::warning::`, not silent — auto-answer a gate, observe an empty egress
allowlist). This skill exists mostly to keep you out of those traps — the Gotchas section below is
the highest-value part. Read it.
> **Version note:** the facts and `file:line` pointers here track `cowork-harness 3.9.0` (baseline
> `desktop-2.9939.2`). If your checkout is newer, prefer the live `--help` and — in a repo checkout —
> `SPEC.md` / `docs/*.md` over this snapshot, and re-run the bundled linter.
## Preflight — make sure the harness can actually run
The 10-second inner loop, once the CLI is on PATH:
```bash
cowork-harness doctor