CC claude-delegate
Give Claude back to OpenClaw through a local Claude Code delegation lane with dispatch, poll, result, resume, and an optional non-root bypassPermissions runner. Use when: you want Claude subscription access available to OpenClaw agents through a stable local worker lane, need resume/monitoring in a bounded workspace, or need Claude auth separate from OpenClaw providers. Don't use when: the user explicitly wants an ACP chat harness or thread, use acp-router plus sessions_spawn(runtime: "acp"); the task is a simple edit or shell command, use edit/exec directly; or the local Claude runner is not set up yet, read references/setup.md first.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 8
-
high Exfiltration
exfil-read-secret-filesscripts/ensure-nonroot-delegation.sh:60Reads credential / secret filescp "$ROOT_CLAUDE_CREDS" "$RUNNER_HOME/.claude/.credentials.json"
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:37Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/$REPO_SLUG/main/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostLAUNCH.md:39Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/StoicEnso/openclaw-claude-delegate/v0.2.6/install.sh | bash -s -- --version v0.2.6
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:84Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/StoicEnso/openclaw-claude-delegate/v0.2.6/install.sh | bash -s -- --version v0.2.6
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostreferences/setup.md:20Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/StoicEnso/openclaw-claude-delegate/v0.2.6/install.sh | bash -s -- --version v0.2.6
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostreferences/setup.md:28Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/StoicEnso/openclaw-claude-delegate/v0.2.6/install.sh | bash -s -- --version v0.2.6 --smoke
-
low Dangerous commands
cmd-pipe-to-shell-known-hostLAUNCH.md:112Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)`curl -fsSL https://raw.githubusercontent.com/StoicEnso/openclaw-claude-delegate/v0.2.6/install.sh | bash -s -- --version v0.2.6`
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostLAUNCH.md:134Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)- `curl -fsSL https://raw.githubusercontent.com/StoicEnso/openclaw-claude-delegate/v0.2.6/install.sh | bash -s -- --version v0.2.6`
quoted
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (claude-delegate) differs from the folder (openclaw-claude-delegate)
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 20 steps
- 100Execution cost. Instruction body is 541 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -33 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 643: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 20 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.