SKILLEMALL.ai

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.

ClawHub Agent Skills author: Antreas Antoniou v1.0.0 MIT-0 9 files body ≈ 829 tokens Open the sourceclawhub.ai analyzed 3 d ago

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

AnalyzerGitHubSoftware developmentInfrastructureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
99
Quality 40%
82
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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-rc scripts/plusultra.py:68
      Writes 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.

    External checks

    ClawHub: suspicious
    The skill is mostly transparent about its workflow gate, but its optional Claude Code setup installs broad persistent hooks that run a PATH-resolved command across sessions.
    LLM: suspicious (high) · 5 Sept 2026