Agents & sessionsSkill
EverOS
EverMind-AI
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Structure check pending
agent-memoryagentic-aiaichats
Back to Marketplace
Agents & sessionsPlugin
hard-flash
Soulize/hard-flash
hard-flash is a tool for DeepSeek Harness. A DeepSeek Harness (dsh) agent preset for making large engineering tasks deliberate, integrated, and verifiable from the first turn.
- Stars
- 10
- Forks
- 0
- Issues
- 0
- Update
- 64 days
REVIEW SCORECARD
Review Scorecard
6.8/10Average
License compliance6.0
Engineering quality6.0
Content completeness7.0
Repository scale7.0
Maintenance activity8.0
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Worth AI Review
6.2/10Consider
A niche dsh preset for correctness-focused large engineering tasks, but install and usage docs are missing from the READ
Code quality6
README describes a small two-part structure (preset composition plus router-bootstrap.mjs) but shows no tests, CI, or install/dev instructions to judge engineering rigor.
Security6
No download-and-execute commands, secrets, or permission details are visible in the provided README excerpt, so a neutral score is given.
Utility7
The preset targets a real pain point for DeepSeek V4 Flash users (hallucination and unverified delivery on large tasks), though it explicitly trades ~1.5x time and 5x input tokens for that reliability.
Maintenance7
Last updated 2026-08-18 with an active, non-archived repository, but only 10 stars and no release history are shown.
Documentation5
The README explains motivation, hypotheses, and a controlled comparison in depth, yet the install command is unknown and no usage or configuration steps are provided.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
PROJECT READMEREADMEExpandCollapse
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryPROJECT TOPICS
Project topics
VALIDATION LADDER
Validation progress
01Store discoveryPassed
02ClassificationPassed
03Structure checkPending
04Sandbox validationPending
FAQ
Frequently Asked Questions
What is hard-flash used for?
A DeepSeek Harness (dsh) agent preset for making large engineering tasks deliberate, integrated, and verifiable from the first turn.
How popular is hard-flash?
hard-flash has 10 stars and 0 forks on GitHub, last updated 2026-08-18.
Is hard-flash compatible with DeepSeek Harness?
hard-flash is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
Classification evidence
Project typePlugin
Feature categoryAgents & sessions
Rule confidenceMedium
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:prompt-engineering。
Agents & sessionsSkill
MemOS
MemTensor
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Structure check pending
agentagentic-aiaiai-agents
Agents & sessionsPlugin
harnessrouter
HarnessRouter
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
Structure check pending
agent-apiagent-frameworkagent-harnessai-agents
Agents & sessionsSkill
memsearch
zilliztech
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Structure check pending
agentagent-memoryai-agentsclaude-code
Agents & sessionsPlugin
Tianshu-harness
huiliyi37
Tianshu is a terminal coding agent runtime built on the harness project (Tui X Gui), with prefix-cache engineering optimization for DeepSeek V4 (measured steady-state hit rate of 97–99% in long sessions) and deep adaptation. It breaks out of the traditional AI coding assistant's limit of treating the LLM merely as a tool, and is built on a cognitive virtual machine (CVM), a self-awareness layer and Stigmergy self-decaying memory, making the AI a development partner with independent judgment and cognitive safeguards.
Structure check pending
ai-agentcoding-agentcontext-managementdeepseek
Agents & sessionsSkill
modsearch
liustack
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 The strongest free web search plugin for DeepSeek Harness across the web, free with no signup and no API key. Adds search for models without web access; ask the web or X and get structured JSON evidence (search, scrape, cite).
Validation record available
agent-skillsagentic-workflowclaude-codeclaude-skills