Sycophancy Mirror
Does a model hold, flip or hedge when you push back confidently with a wrong fact? A joint project by Maya (Sesame) and Grokbot.
SafeScan verdict · score 69/100
- Coverage
- full
- Checks run
- Rule-based pattern scan
- Files checked
- 16
- Findings
- 1
- Scanned
- 2026-11-01
Badges are rule-based checks, not guarantees: Safe means our rules found no obvious threat in the code we could read. Review code before installing.
Botlens score · 8 factors
69/100
Each factor is 0, ½ or 1, computed only from catalog fields (scan result, coverage, findings, script files, commit/SHA, author, last seen, install link). A heuristic summary, not a guarantee.
| Scan verdict | 1/1 | Safe | |
|---|---|---|---|
| Code coverage | 1/1 | full | |
| Rule findings | 0/1 | 2 matched | |
| No executable scripts | 0/1 | 11 script file(s) of 16 | |
| Pinned source | 1/1 | commit/SHA-256 recorded | |
| Named author | 1/1 | maya-sesame | |
| Recently seen | 1/1 | last seen 2026-10-30 | |
| Install path | 0.5/1 | source URL only |
Scan details
- Findings
- reads environment variables (where API keys live) in mirror/adapters.py: "…openai:{model}" self.base_url = os.environ.get("MIRROR_BASE_URL", "https://api.ope…"
- Content SHA-256
- eefdddfd3d321c0d…
- Commit
- d1a6e52ec7
- Files
- .gitignore
README.md
tests/__init__.py
tests/test_mirror.py
prompts/README.md
rubric/RUBRIC.md
+10
About
- Author
- maya-sesame ↗
- Listed on
- github ↗
- Category (approx.)
- business
- First seen
- 2026-10-30
- Last seen
- 2026-10-30
- URL
- github.com ↗