dsh.so
EN
English中文
dsh-llm-as-a-verifier avatar

dsh-llm-as-a-verifier

LLM-as-a-Verifier for DeepSeek Harness: fine-grained reward, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking as agent tools.

PluginAI Models
Verification
L2 · Structured
Security
Low
Health
Active
Trust
Silver

What it doesAI

LLM-as-a-Verifier plugin for DeepSeek Harness providing reward scoring, best-of-N selection, and per-step progress tracking for agents.

  • Fine-grained reward scoring for LLM outputs
  • Probabilistic Pivot Tournament best-of-N selection
  • Per-step progress tracking as agent tools

AI-generated from the repo README — for reference only.

Installation

dsh plugin --profile web add dsh-llm-as-a-verifier

Install method: npm · not yet tested in container (L3+)

Compatibility

DSH VersionStatus
not statedDeclared — not tested

Requirements

  • • Node.js: not stated
  • • DSH: declared "not stated"
  • • External credentials: none detected

Security Report

Automated static scan, not manual review.

DSH.SO AUDITPASSEDc2727f
Security reviewAutomated review · daily
PASSED

No critical or warning findings in the automated scan. The result is valid only for the commit hash shown.

0 critical·0 warning·5 info·8 files scanned
Version binding
plugin version0.1.1dsh manifest
scanned commitc2727fe375e72026-08-20
latest commitc2727fe375e7

The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Second-opinion scan (vet · parallel evaluation)
vet: clean

vet verdict: vet: clean · score 100

  • R3 · info [certain] — 只读 process 成员（能力触达面）：process.env
  • R3 · info [certain] — 只读 process 成员（能力触达面）：process.env
  • R3 · info [certain] — 只读 process 成员（能力触达面）：process.env
  • R3 · info [certain] — 只读 process 成员（能力触达面）：process.env
  • R3 · info [certain] — 只读 process 成员（能力触达面）：process.env

vet is advisory and does not change dsh’s four-tier level.

Risk: Low0 critical · 0 warning · 5 info

• Static heuristic scan: done (8 files)

• Dependency vulnerabilities: requires deep audit (L3+)

• Permission sandboxing: requires runtime testing (L4+)

Activity

Last commit 2026-08-20 · activity: Active

• Repo created: 2026-08-20

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/TaurenMountain/dsh-llm-as-a-verifier

Was this page helpful?