AC plus-ultra
Run a Byzantine 2+1 plan before consequential work and a fresh, plan-blind reality check afterward. Use when the user asks for Plus Ultra, maximum rigor, independent proposals, enforced verification, or help responding to a Plus Ultra hook gate. Claude Code can enforce the loop through the included hook adapter; on Codex and other hosts it is a convention unless separately wired and verified.
Run a Byzantine 2+1 plan before consequential work and a fresh, plan-blind reality check afterward.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-shell-rcscripts/plusultra.py:68Writes to a shell startup file (string literal in code, not executed; code comment)# `cat <<EOF > ~/.zshrc` redirects. An earlier version scrubbed from the tag to the
code literalcomment
Files scanned: 8. 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 57/100
- 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
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 829 tokens
- 100Running it twice. No mutating operations
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
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 395: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.