Sider Task Reviewer: another model of your choice (any provider dsh has, with its reasoning effort) reviews the task the current conversation is doing or has done. Review the last turn, the whole conversation or turns N–M; look at the conversation, the files it wrote, or both; quick, or deep, where the reviewer may also read files, list folders and search. Read-only throughout: neither the plugin nor the reviewer ever edits a file or runs a command (no tests, no builds, no git); anything that needs a change or a command run is written as a suggestion for the main conversation to do. Agent-style reviewers such as Antigravity (Gemini through the agy CLI) are run in their read-only plan mode. Each review gives a verdict (pass / doubt / fail) and findings with severity, evidence and a suggestion, saved per conversation and exportable as Markdown. The reviews of one conversation remember each other: each new review is sent with the earlier conclusions and the discussion, so the reviewer stays consistent, and you can discuss the latest review with the reviewer in the panel (its replies can go into the input box). A right-sidebar tab holds the settings and reports; a shield beside the input box reviews the last turn on a left click and puts the suggestions into the input box, and opens a menu on a right click. Findings reach the working model only when you press a button, or in continuous review, which sends them, waits for the fix and reviews again until a review passes or the round limit (5 by default). Optional live review after every turn only reports. Four built-in prompts (work done, derivations, literature surveys, plans) that you can edit, plus your own. Common secrets are hidden before anything is sent. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
Install
# from a prebuilt release tarball
dsh plugin --profile web add "https://github.com/HanYu-me/dsh-sider-task-reviewer/releases/latest/download/dsh-sider-task-reviewer.tgz"
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:HanYu-me/dsh-sider-task-reviewer
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★ 735
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.
oriliz/agent-crop★ 198
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.
icyaaaww/dsh-soul★ 108
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★ 77
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.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.