Score
Plugin for DeepSeek Harness
Repository ownerPerryLinkdsh-score
Multi-dimensional quality scoring for DeepSeek Harness plugins: scores a repo or npm package across install success (consuming dsh-test-drive results), maintenance activity, documentation completeness, security scan, and protocol compliance — every conclusion backed by real CLI evidence with audit timestamps.
How to install
dsh plugin --profile web add github:perrylink/dsh-scoreSuggested commands are derived from the catalog record. Review the repository README, requested permissions, and source before installation. Read the full guide.
What this plugin does
Multi-dimensional quality scoring for DeepSeek Harness plugins: scores a repo or npm package across install success (consuming dsh-test-drive results), maintenance activity, documentation completeness, security scan, and protocol compliance — every conclusion backed by real CLI evidence with audit timestamps.
Repository README
View on GitHubThis content is loaded directly from the repository HEAD and rendered safely in your browser. It is maintained by the repository author and is not verified or endorsed by this directory.
Repository and source evidence
This public repository was verified through the GitHub API. The catalog source links the plugin to this repository, but directory inclusion is not an official endorsement.
- Repository owner
- PerryLink
- Author
- No independently verified author field is available
- Source
- https://github.com/AdamPlatin123/awesome-dsh-plugins
Example configuration
Use the repository README and manifests for plugin-specific configuration. This command inspects the active profile.
dsh --profile web --dump-configSupported DeepSeek Harness versions
Awesome DSH matrix: Compatible (source label: 可用)
The compatibility evidence is “Awesome DSH matrix: Compatible (source label: 可用)”; its DeepSeek Harness mainline reference is commit 5badb15009ae; plugin source anchor: “unknown”.
Environment, permissions, and dependencies
Environment
Primary language: TypeScript; runtime version not verified.
Permissions
Permissions are unverified; review the README, environment variables, and external access.
Dependencies
Dependencies are unverified; use the repository manifest and lockfile.
GitHub metadata
- Stars / forks
- 12 / 0
- Last repository update
- October 7, 2026
- Latest release
- v0.2.19 · October 5, 2026
- License
- Apache-2.0
- Default branch
- main
- Available / archived
- Publicly reachable and not archived
Installation safety
Third-party plugins can execute code in Harness. Review source, dependencies, build scripts, and permissions, then test in isolation.
Git installs may run prepare/build scripts outside the sandbox; trust the source and pin a commit.
Read the plugin safety guideCommon errors and troubleshooting
No plugin-specific troubleshooting was collected; these are general checks.
- 1. Plugin missing after installation
Confirm installation and launch use the same profile, then run dsh --profile web --dump-config to check whether the bundle entered the composed configuration.
- 2. Git dependency build is blocked
pnpm 10+ may block prepare scripts. Only after reviewing the source, add the exact package key reported by pnpm to allowBuilds, then retry.
- 3. Version or configuration mismatch
Check the repository README, releases, and compatibility evidence. Do not treat directory-wide commands as promises from the plugin author.
Security
More plugins in this category
Cc Safety Net
kenryu42 / cc-safety-net
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
Aegis
GanyuanRan / Aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
K8e
xiaods / k8e
k8e.sh - OpenSource Agentic AI Sandbox Matrix
DeepSec
Unclecheng-li / DeepSec
DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.
Jev Dsh Decision
Devin-AXIS / jev-dsh-decision
Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。
Blender Plugin
sixtysevenlf / dsh-blender-plugin
DSH x Blender direct realtime plugin v1.0 — let an AI model drive Blender over a direct TCP channel: viewport frames, custom-angle renders, inner-loop search, render profiling, safe decimation, headless offload, one-call GUI launch (15 tools + blender_rt_plan: 28 families / 183 ops). 配套 skill：sixtysevenlf/dsh-skill-blender-modeling
Jev Plugin
luobosibing2 / dsh-jev-plugin
Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev as a System One decision layer for agent selection, supervision, corrections, and approvals.
Turn Rewind
Anionex / dsh-turn-rewind
deepseek harness对话和代码状态回退插件 | DSH — rewind conversation and workspace state, powered by a persistent Change Ledger