Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
11 plugin trovati
dsh-auto-approve
jiao-xxx/dsh-auto-approve
Aggiunge un preset di permessi `auto` tra workspace-write e danger-full-access: un classificatore concede una volta le escalation di routine della sandbox, mentre le richieste pericolose o incerte vengono comunque inoltrate a un essere umano.
dsh-workspace-acl-allow
lovezi0/dsh-workspace-acl-allow
Preautorizzazione delle aree di lavoro Windows: aggiunge alle cartelle dichiarate dall’utente una ACE DACL di controllo completo (incluso WRITE_OWNER, necessario per avviare il sandbox di dsh ≥0.1.7), eliminando richieste ripetute di elevazione. Autorizza solo percorsi aggiunti esplicitamente e blocca le cartelle di sistema. Solo Windows.
dsh-full-with-approval
zjuhbh/dsh-full-with-approval
Quarto preset di permessi per dsh: sessioni senza restrizioni e con GPU (danger-full-access) con approvazione utente per singola operazione per scritture fuori dal workspace o su percorsi protetti (.git/**, .env*); implementato solo come bundle sopra l'hook ask ufficiale tools/pre-execute, senza modifiche al core.
dsh-ember
realoiyo/dsh-ember
Composer UI for DeepSeek Harness that does two things. The reasoning-effort row in the model menu becomes a continuous slider drawn on the row itself, with the rungs read live from the model adapter so any ladder length works; each rung paints its own ember plume into a canvas behind the knob. Separately, the permission trigger renders in the theme error colour whenever full access is the active preset, including its row in the permission menu.
dsh-full-access-switch
xtd1145/dsh-full-access-switch
Interruttore Full access una tantum per DeepSeek Harness: le nuove sessioni (aree di lavoro e conversazioni) iniziano con `danger-full-access` e saltano la conferma Full access per sessione. Installabile come bundle dsh o tramite script di patch.
dsh-perm-guard
a903067276-rgb/dsh-perm-guard
Guardia dei permessi con auto-approvazione: un livello intermedio tra workspace-write e danger-full-access — consente automaticamente le operazioni sicure nelle directory attendibili e chiede sempre conferma a un operatore umano per quelle distruttive, con 11 interruttori per categoria e un registro di controllo.
dsh-auto-approval-plugin
styxnether/dsh-auto-approval-plugin
Un livello di permesso intermedio per DeepSeek Harness tra workspace-write e danger-full-access: approva automaticamente i comandi innocui e le operazioni destinate ad aree attendibili configurate, al di là del workspace corrente
dsh-turn-approval
arrow949/dsh-turn-approval
Approvazioni con ambito di turno "Consenti per questo task": consente automaticamente le escalation `danger-full-access` corrispondenti solo per il task corrente, poi scadono
dsh-hard-gate
yyfdfsyyf-source/dsh-hard-gate
An independent permission gate above the built-in sandbox. It blocks writes outside the workspace and to protected paths even under danger-full-access, refuses whole-file overwrites without a complete fresh read, and keeps ZIP restore points plus Recycle Bin copies before destructive actions.
dsh-workspace-only-plugin
devilspiderx/dsh-workspace-only-plugin
Restrict the file access of agents in any sandbox mode (read-only / workspace-write / danger-full-access / auto) to the session workspace, and ask the user to rule on cross-border access. Each session can also use the gear selection box next to the composer to relax the cross-border gate to 「 read-only outside workspace 」 or 「 fully release 」.
dsh-sandbox-noop-escalation
zzstar101/dsh-sandbox-noop-escalation
Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.