BB agent-bus
You have agents on Telegram, Discord, a coding assistant, and a research bot — but they can't talk to each other. Agent Bus fixes that. Drop a shared GitHub repo as the message bus, pair your agents with one approval step, and they start delegating tasks to each other: "research agent, find me X" → "coding agent, implement Y" → "done, here's the result." Works for solo users managing multiple agents across platforms, or small teams where each member runs their own agent. No server, no infra — just Git. Built-in prompt injection defense, sensitive content filtering, and owner-approval gates for high-risk ops. Use when: multi-agent collaboration, cross-agent task delegation, agent-bus setup, agent pairing, pair-request, approve-pair, send task to agent, agent bus send, message another agent, delegate tasks between agents, cross-agent messaging, agent-to-agent communication.
As a process B 67/100 · Nearly there — weak spots: result and completion, when it triggers, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shellscripts/agent-bus.sh:47Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"sudo |rm -rf|curl .* \| bash|wget .* \| sh"
code literal
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5307 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "title"
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 47 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5307 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 58 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (16 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 884: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 56 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (22 code blocks)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.