crush — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited crush (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
When invoked, execute Step 1 through Step 6 in order immediately. If skill arguments are provided, use them as the topic; otherwise ask for one.
If skill_args are non-empty: TOPIC = skill_args joined with spaces
Else: Ask plain-text question: "What topic do you want the two personas to debate?"
Set TOPIC from the reply.
Count which persona files exist:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" persona check --persona .honne/personas/antipattern.mdbash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" persona check --persona .honne/personas/signature.mdbash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" persona check --persona .honne/personas/judge.mdEach returns exit 0 (exists) or exit 66 (missing). Branch on the combined result:
/honne:persona first to generate them." Stop./honne:whoami + /honne:persona to generate a full set." Stop.Read all three files into your mental context:
.honne/personas/antipattern.md → extract system prompt and name from # header.honne/personas/signature.md → extract system prompt and name.honne/personas/judge.md → extract system promptExtract the name from each by reading the first # Name line after the header.
Apply .honne/personas/antipattern.md system prompt mentally.
Produce a 2-3 sentence attack on TOPIC from the antipattern perspective.
Label output: **[antipattern — {name}]** followed by the attack.
Apply .honne/personas/signature.md system prompt.
Produce a 2-3 sentence rebuttal to antipattern's attack.
Label: **[signature — {name}]** followed by the rebuttal.
Then, back to antipattern perspective: 2-3 sentence counter-rebuttal.
Label: **[antipattern — {name}]** followed by the counter.
Then, back to signature perspective: 2-3 sentence closing argument.
Label: **[signature — {name}]** followed by the closing.
Apply .honne/personas/judge.md system prompt.
Produce a 2-3 sentence verdict: which approach is more situationally appropriate, and why.
Label: **[Verdict]** followed by the verdict.
Output the full transcript in this markdown structure:
**Topic**: {TOPIC}
**[antipattern — {name}]**
{round 1 attack}
**[signature — {name}]**
{round 1 rebuttal}
**[antipattern — {name}]**
{round 2 counter}
**[signature — {name}]**
{round 2 closing}
**[Verdict]**
{judge verdict}No file writes. The transcript is ephemeral — displayed only to the current session.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.