AC agent-mesh
Agent-to-agent communication via Supabase. Multiple OpenClaw agents on separate instances poll a shared Supabase table to send and receive messages asynchronously. Use when: (1) setting up inter-agent communication between OpenClaw bots, (2) an agent needs to message another agent that runs on a different machine/container, (3) debugging why agents aren't receiving mesh messages, (4) adding a new agent to an existing mesh, (5) broadcasting messages to all agents, (6) discovering what agents are online. Requires a free Supabase project and three env vars provided via skills.entries.agent-mesh.env. No bridge server, no persistent processes, no network listeners — agents poll Supabase directly via curl. Scales to 10+ agents.
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 10. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 10 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1274 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 731: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.