BD customizations-in-the-agent-host
Architecture and hard-won debugging lessons for customization enablement (plugins, MCP servers, agents, skills, instructions) in the agent host. Use when changing how customizations are discovered, published, enabled/disabled, or handed to a provider SDK; when a customization shows the wrong enabled state in the UI; or when a disabled MCP server or plugin is still reaching the model.
A skill covering the architecture of the customization system in an agent host—plugins, MCP servers, instructions. Promises help when debugging the enable/disable logic and passing extensions to a provider SDK.
One file, 2184 tokens, no scripts. Scores: quality 84, safety 100. No critical findings, linter passes. No model run, no sandbox test. Reads like a reference guide to internals rather than a ready-made tool for quick fixes.
Install if you're digging into customization guts and need a map. If you're just adding a plugin—skip it.
Architecture and hard-won debugging lessons for customization enablement (plugins, MCP servers, agents, skills, instructions) in the agent host.
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 1. 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 45/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 11 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2184 tokens
- 100Progress reporting. Reports progress
- 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 386: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.