dsh-anchored-subagent
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
169 results
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
V0 capability-disclosure scanner for DeepSeek Harness (DSH) cordis plugins: reports which sensitive services (credentials/shell/approval/sandbox/fs/tools...) a plugin declares or references before you trust it.
Governed platform access for DeepSeek Harness — no credential on the machine
DeepSeek Harness 密钥保险库插件:密钥自动脱敏、自动收纳、密码本设置页、跨重启持久(官方 profile bundle)
DSH plugin: anonymize workspace-external file paths before model requests with user confirmation
DeepSeek Harness plugin: a citable append-only JSONL of filesystem touches — path, op, sha256 before and after — carrying no file contents
Harness 事件流审计面板:观察事件类型、分发模式、计数与最近事件,帮助插件作者理解 harness 内部发生了什么
Agent harness 配置系统:agents/skills/hooks/rules 四层分工、instincts 持续学习(自动学模式、聚簇成技能)、AgentShield 安全审计(secrets/权限/hook 注入/MCP 风险)、Unified Memory Vault 跨 harness 共享、GateGuard 破坏性命令门卫。受 affaan-m/ECC(185k★ MIT)启发。
Record and compare project development environments without storing secret values.
Secure credential vault for DeepSeek Harness: store GitHub/npm/API tokens (secrets never leave the host), run gh/npm/npx/node/git with the token injected in the environment, and manage tokens from a Settings page.
Configurable auto-approval for DeepSeek Harness: intercepts approval/request and answers allowed-once/rejected by policy (allow-all / allowlist / deny-always), with a full audit log — so the human is only asked when the policy says so.
DeepSeek Harness plugin: plants a canary string in model-visible context and denies any tool argument or outbound URL that echoes it back
Project DeepSeek Harness tool, approval, and result facts into a bounded action lifecycle ledger.
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
【实验性】只读安全审计模式插件(自动只读、工具级白名单、强制交付选择)· EXPERIMENTAL plugin for the read-only security audit mode (auto read-only, tool allowlist gate, mandatory delivery choice);日常使用推荐 dsh-presets 仓库的原生纯预设版。
DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费,峰时正好是上班时间。
Codex-inspired managed approval for DeepSeek Harness: risk-based MCP review, one-time grants, explicit denials, and human fallback on reviewer failure.
Local, zero-network, fail-closed secret preflight for DeepSeek Harness model requests.
DSH bundle: re-inject KEY/PASSWORD/SECRET/TOKEN variables from the launching environment into dsh bash subprocesses under their original names
HashiCorp Vault backend for the DeepSeek Harness credential seam: central secrets, AppRole machine auth, rotation without restart, and no long-lived provider key on the agent host
Workspace tools for DeepSeek Harness: per-workspace default Agent preset and permission preset for new sessions, using only official extension points (no DSH patches required).
DSH plugin for background security audits, secret leakage detection, and command safety
Read-only MCP server exposing the dsh-plugin-certification registry: certification grades, snapshots and five-dimension evidence for DeepSeek Harness plugins.
DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.