parallel-search-skill (incl. Grok Build bench)

Multi-agent deep-search SKILL.md pack with a harness bench that includes Grok Build alongside Claude Code and Kimi Code.

View source ↗
SafeScan verdict · score 56/100
Coverage
full
Checks run
Rule-based pattern scan
Files checked
590
Findings
4
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.

View source ↗
Botlens score · 8 factors
56/100

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 verdict1/1Safe
Code coverage1/1full
Rule findings0/17 matched
No executable scripts0/120 script file(s) of 590
Pinned source1/1commit/SHA-256 recorded
Named author0/1unknown
Recently seen1/1last seen 2026-10-30
Install path0.5/1source URL only

Scan details

Findings
  • Hand review 2026-11-01: No concrete threat in stored content.
  • lookalike of google.com: ai.google.dev
  • link has a template placeholder that fills in user data: https://generativelanguage.googleapis.com/v1beta/{model=models/*}:generateConten
  • reads environment variables (where API keys live) in bench/grok_usage.py: "…True, env=dict(os.environ, **GROK_ENV), stdin=subprocess.DEVNULL)…"
Content SHA-256
6227c7665d04c7e5…
Commit
45834570c8
Files
.gitignore
LICENSE
README.md
bench/README.md
bench/arms.json
bench/devin_shim.py
+584

About

Author
chenghaoYang ↗
Listed on
github:RongleCat/awesome-grok-bot ↗
Category (approx.)
agentops
First seen
2026-10-30
Last seen
2026-10-30
URL
github.com ↗
Get the Botlens skill