Per-conversation Grill switch in the composer tool row (also /grill on and /grill off): while it is on, the agent analyzes every request for ambiguity, missing information and contradictions, asks focused questions with 2-4 concrete options and a repair proposal, and plans or executes only after every blocking question is resolved. Trivial work is done directly with a one-line reading; non-trivial work is planned and stopped for approval. State is folded from the session log, so reload, resume and fork restore it, and a delegated subagent reports unresolved questions instead of asking.
Install
# from a prebuilt release tarball
dsh plugin --profile web add "https://github.com/Kingzhoudk/dsh-grill/releases/latest/download/dsh-grill.tgz"
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:Kingzhoudk/dsh-grill
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
Links
More in this category
FuRongJun-1999/dsh-memory★ 709
White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
Clearailhc/clearai-dsh★ 702
An agent preset for evidence-checked research: every step advances only through system-verified observations, L3+ claims go to an independent evaluator, and the session folds into a replayable ledger that grows into a browsable domain ontology. Requires DSH >=0.1.7-alpha.1.
icyaaaww/dsh-soul★ 96
Records recurring task corrections and tool failures locally, then compiles them into changes to eight harness components through explicitly started evolution, paired baseline/candidate checks, trial activation and rollback. Includes a budget and audit ledger; requires Node.js 24+ and a compatible DSH 0.2.1-rc.2 or later 0.2.x host.
MichengAI/dsh-pua★ 76
Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.
kenz1117/dsh-engram★ 75
Cross-session long-term memory as a local SQLite store: dual scopes (user + per-git-origin project), hybrid FTS5 + local-vector retrieval fused with RRF, an evidence gate that forces an explicit sufficiency judgement, provenance audit chains, SM-2 spaced-repetition review, consolidation distillation and decay forgetting, and a nine-view "Memory Palace" sidebar panel. 22 narrow-parameter tools, no external service, no API key, no Docker.
pk14742952-AD/dsh-host-rsi★ 39
Reflective self-evolution plugin for local Qwen3.8 27B/3.8 Flash and online APIs: a coding-loop convergence steerer curbs Qwen3.8 27B/Flash repeated-verification deep-thinking to converge faster and cut thinking time; a five-state delivery guard detects and corrects stuck turns and infinite loops; model-agnostic host logic, mostly compatible with online APIs; per-use continual self-improvement with counter-reason self-checks, critic escalation, inverted-index memory retrieval, coding-loop convergence steering, and a five-state delivery guard.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.