CD agi-farm
Interactive setup wizard that creates a fully working multi-agent AI team on OpenClaw. One command bootstraps agents, SOUL.md personas, comms infrastructure (inboxes/outboxes/broadcast), cron jobs, auto-dispatcher (HITL + rate-limit backoff + dependency checking), and a portable GitHub bundle — all customized to team name, size (3/5/11 agents), domain, and frameworks (autogen/crewai/langgraph). Includes a React + SSE live ops dashboard with file-watcher (~350ms push latency) and persistent macOS LaunchAgent. Model-selection guidance built in. Commands: setup | status | rebuild | export | dashboard | dispatch
As a process D 41/100 · Unfinished process — weak spots: steps, result and completion, when it triggers
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 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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 7
-
high Dangerous commands
cmd-persistenceSKILL.md:362Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/ai.coopercorp.dashboard.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:363Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.coopercorp.dashboard.plist
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokendashboard-react/package-lock.json:298High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…SzS+cfgl…B0A==",
detector -
low Secrets in code
secret-high-entropy-tokendashboard-react/package-lock.json:312High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…7pY+zoMV…h0x/Ptw8…8dg==",
detector -
low Secrets in code
secret-high-entropy-tokendashboard-react/package-lock.json:329High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…b00+Gxjx…zRc/oZwU…hzA==",
detector -
low Secrets in code
secret-high-entropy-tokendashboard-react/package-lock.json:397High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha512-vHk/hA7/1Ack…wbo+jaSh…Gtl+A5zq…HFg==",
detector -
low Secrets in code
secret-high-entropy-tokendashboard-react/package-lock.json:431High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…Dsc+j03S…0oA==",
detector
Files scanned: 38. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 41/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, git, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4272 tokens
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +4Description does not say when NOT to use the skill (false activations)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 615: enough signal without eating the budget
- +4Structure: 33 headings
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.