A higher standard
of evidence for
software security.
We audit your source code against ten frontier language models in parallel, then commission an eleventh — the scorer — to adjudicate consensus. The result is a single, signed report that you can publish, cite, or hand to a board.
Engagements of Record
Clavitor·Postern Inc.·Zentry Labs·Marlin·Osprey·Courant
The Procedure
Ten readers. One verdict.
Zero ambiguity.
Submission
Drag your source directory or paste a repository URL. We concatenate every file, compute a SHA-256 hash, and pair the corpus with a security checklist tailored to your language and domain.
Examination
The same prompt is dispatched to ten frontier models in parallel — Claude, Gemini, GPT, Grok, Llama, Qwen, DeepSeek, Kimi, Codestral, MiniMax. Each audits independently, blind to the others.
Adjudication
An eleventh model — the scorer — reconciles all ten reports. Findings are cross-referenced, consensus-weighted, and compiled into a single signed scorecard.
The Output
A specimen
that earns a signature.
Every report carries a SHA-256 content hash, a timestamped seal, and the full findings table — severity, consensus count, and penalty. The scorecard is deterministic: same inputs, same score.
View published specimens →| Finding | Severity | Consensus | Penalty |
|---|---|---|---|
| Timing side-channel in HMAC compare | Medium | 4 / 10 | −3 |
| No zeroization of key material | Medium | 6 / 10 | −3 |
| Missing HKDF length validation | Low | 3 / 10 | −2 |
| Nonce reuse risk in stream API | Low | 2 / 10 | −1 |
Tariff
Two services. Both deliver
the full audit.
Information
Per audit engagement
- Full ten-model audit with consensus scoring
- Detailed findings table with severity and penalty
- SHA-256 content hash for provenance
- Markdown report delivered to your dashboard
- Private — visible only to you
Publication
Per audit engagement
- Everything in the Information tier
- Signed PDF with certificate-style cover page
- Permanent public URL for the report
- Embeddable SVG badge for your README
- Listed in Published Reports with scorecard
- Referenceable by auditors, boards, and clients
An argument from first principles
One model can be wrong. Ten models, asked the same question independently and reconciled by an eleventh, are evidence.