BB codex-delegate
Decide when to delegate a task to Codex and when to keep it in the main agent thread. Use when the work is code-heavy, repo-heavy, multi-file, environment-sensitive, or likely to consume too much context in the main session. Especially useful when acting like a project manager or tech lead: define the task, choose whether Codex should handle it, and decide what must still be validated by the main agent.
As a process B 65/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Decide when to delegate a task to Codex and when to keep it in the… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 58 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 799 tokens
- 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)
- +4No input/output examples
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 406: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 58 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.