Plugins

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.

Summarises the case evidence, diagnosis, repair procedure, parts list and cost-option comparison for a motor into a Markdown repair recommendation report with data provenance.

Group-chat multi-agent orchestration console for DSH: autonomous decision-making, task dispatch, verification and iterative optimization for long tasks; bundles its own backend, installs with `dsh plugin add`.

Keeps long DSH sessions alive when a model channel starts failing: daruma takes over after the in-box retry gives up, trips a self-healing circuit breaker on repeated 429/5xx or a terminal error, and moves the next request to another channel in your chain. A panel beside the composer picks the backup by hand, switches show up as rows in the conversation, and every decision lands in a durable JSONL audit log.

Decision log for DeepSeek Harness: record key decisions (chosen option + why) into a versionable DECISIONS.md via decision_log / decision_list / decision_audit tools, and auto-inject the summary into future sessions so decisions stay traceable and are never re-litigated.

Forces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every

Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.

Porte de sécurité à l'exécution sur le pipeline d'outils : refuse les appels nommant des hôtes hors d'une liste d'autorisation de sortie, caviarde les identifiants dans les résultats au niveau de la valeur canonique et pas seulement du contenu affiché, et consigne chaque décision dans un journal d'audit JSONL ; livré en mode surveillance seule.

Preset d'agent de rédaction de contrats : workflow juridique en 11 étapes avec revue IA en parallèle à 5 voies, portes de décision et packs de domaine pour les contrats généraux, de travail et d'investissement en capital.

Tableau de focus pour les agents DeepSeek Harness : des notes durables tenues par le modèle dans le workspace de session, qui fixent l'objectif, les contraintes et les décisions à travers la compaction et les sessions, avec injection automatique dans le contexte, archivage à l'effacement et panneau web optionnel.

Suivez les décisions humaines pour les branches de session DSH associées : conserver, supprimer ou donner suite avec motifs, étiquettes et liens externes.

La couche d'autorité pour l'IA agentique, en plugin DeepSeek Harness. Régit chaque appel d'outil selon vos règles métier via le point de décision de politique TapPass /v1/govern.

Typed System One decision service for DeepSeek Harness plugins, with an agent tool for yes/no checks, classification, and scoring.

三重一大决策台账核对（按前置研究、会议审议与决议记录核对程序留痕，仅提示差异，不作出定性结论）

Compiles a rough need into a versioned task book (goal / context / constraints / acceptance / decisions / open gaps, all numbered) and hands it to any AI window losslessly: the receiver must pass a read-back handshake — restate, list gaps, declare READY — before work starts; /answer closes gaps with an automatic version bump, /forge-list tracks which window holds which version.

Turns a DSH session into a self-contained interactive HTML mind map of its topics, conclusions, decisions, todos and open questions, and reports what changed since the previous run.

Connects dsh to the GreatArrow.ai MCP server over Streamable HTTP, so the agent can search and save workspace memories, tasks and decisions shared with your other AI clients; a config-only bundle that reads the token from great-arrow.token in the dsh home, never from the environment.

One-click TokenDance gateway access for DeepSeek Harness: OAuth sign-in stores the API key, a live model catalog with per-model visibility, and agent tools for chat, image generation, video generation and typed decisions.

Drive a browser from one natural-language goal: a decision service picks the next operation and target from an indexed element table, so a DSH session spends one tool call instead of one turn per click.

Local non-generative decision layer for DeepSeek Harness: the phocinae_ask / phocinae_gate tools backed by a Phocinae-Largha-150M-v1 server, plus a fail-closed approval gate on tools/pre-execute with a calibrated-confidence escalation signal

A structured decision layer for the DeepSeek Harness agent loop: a danger-call gate, output self-check, tool narrowing, and loop guard backed by a pluggable adjudication model.

A `jev` tool that asks Jev (TypeSafe System One) typed yes/no, choice and score questions about one block of text and returns probabilities and confidence, with the provider and API key configured per user in Settings, a judgment ledger with its spend, and daily call and token caps.

A continuation of simon300000/dsh-auto: the Auto Approve permission preset for the DSH Web UI reviews each approval with one single-shot model call instead of a reviewer subagent, auto-approves only the actions that pass and hands the rest to human approval, and remembers confirmed decisions as project- and global-scope allow/deny lists, with an approval timeline in the right sidebar.