BD agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
A skill for embedding side effects into the agent-host chat lifecycle. Promises to handle context injection, history transformation, and protocol-action interception through AgentSideEffects and AgentService.
One module with 4084 tokens, no critical issues. Linter passes, safety score maxed out. Quality dropped to 79 due to process score at 47—hints at incomplete documentation or missing usage examples. No medium or low findings, but that just means checks didn't catch obvious errors, not that everything's solid.
Wide platform support: Claude, Cursor, DeepSeek, Mistral, and eight more. Sandbox didn't run, models untested—you'll verify real-world behavior yourself.
Install if you specifically need agent-host lifecycle handlers. Without battle-tested examples and model validation, the risk surface is larger than usual.
Build and review cross-cutting agent-host chat behavior through lifecycle contributions.
As a process D 47/100 · 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
- note
edit-residuethe text marks something as outdated (lines 147): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 14 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4084 tokens
- 100Steps. 41 steps
- 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 10 top-level sections: this looks like several domains in one skill
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
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 301: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.