CB orchestrate
Runs a multi-model orchestration workflow led by the session’s strongest available model, Fable or Claude Opus. Delegates mechanical work to a fast Sonnet subagent, wide reasoning to high-effort Opus subagents, and high-stakes or fresh-perspective work to Codex or a different-vendor GPT-6 Astra peer (`gpt-6-astra` by default). Detects the lead from session context, while `--lead fable` and `--lead opus` override it. Under Fable, judgment remains with the lead. Under Opus, parallel Agent fan-outs or a dynamic Workflow handle delegated phases. Use to orchestrate, delegate, fan out, obtain a decorrelated Codex opinion, run blind Opus-Codex cross-checks, or act as tech lead.
Runs a multi-model orchestration workflow led by the session’s strongest available model, Fable or Claude Opus.
As a process B 73/100 · Nearly there — weak spots: result and completion, when it triggers, execution cost
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Agent Workflow Bash Read Write Edit
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10373 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 10373 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 67 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (10 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
- +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 679: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.