A "Development planning and delivery" agent preset in which the expensive main model only plans, dispatches and reviews: four delegation tools (recon, review, scribe, develop) spawn child agents in-process, the build subagent reports straight back to the main window, and a subagent model guard keeps every child on the provider and model chosen on the settings page while the main session is never re-routed. The build subagent may be any preset already installed on the host. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:hongcha-dsh/dsh-dev-plan-presets
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★ 717
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★ 100
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.
oriliz/agent-crop★ 73
Times AI coding sessions, nudges long-running turns, and keeps a local work ledger with a collector-health dashboard, so you can see where the time actually went. It also records retrospectives and routes each lesson back into agent instructions, skills, or tooling.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.