DSH Marketplace

dsh-research-report

PerryLink/dsh-research-report

Verifiable research-report engine for DeepSeek Harness with a content-addressed evidence ledger, versioned sealed reports where every claim carries a verification verdict and the manifest hash seals the directory, and retrieval orchestration that reuses the ctx.web and ctx.jobs seams.

2132TypeScriptApache-2.0Source

Install

Add dsh-research-report to DeepSeek Harness

Install into

via npm

Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.

via GitHub · npm package

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

What happened when we ran it

Installed cleanly when we ran it

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run yesterdayon DeepSeek Harness 0.2.2-rc.5.

Show it in your README

install verified — dshmarketplace

For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.

Due diligence

Before you install dsh-research-report

  • Source of record: PerryLink/dsh-research-report — present in the community registry that DSH's own plugin market installs from.
  • Licensed under Apache-2.0.

Security

What installing dsh-research-report runs

Build scripts

No build script was blocked in our run.

Source: our sandbox install on DeepSeek Harness 0.2.2-rc.5, yesterday.

Install hooks

package.json declares no preinstall, install or postinstall script.

Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.

README mentions

Neither shell commands nor credentials.

Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.

Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.

The AI take

What it is — A DeepSeek Harness plugin that emits a versioned sealed research report: each claim binds to a content-addressed evidence snapshot with a verification verdict, and a manifest hash seals the directory.

Who it is for — You are drafting a client- or audit-facing industry or policy brief in DeepSeek Harness and still lack frozen source snapshots that each claim can be checked against before delivery. Write-ups that live as paraphrase and synthesis, with almost no locatable figures or quotations, are not the shape of output this engine can certify.

Watch out — It installed on a fresh profile and the harness registered it. research-report events stay out of the session log; the ledger journals are the durable store. Checks are literal byte matches only, with no semantic or embedding layer. Node must be ^22.19.0 or >=24.0.0, ESM only; ctx.web, ctx.jobs, and dsh-data-quality remain optional for capture, background assembly, and dataset cross-checks.

The verdict — I treat it as archive infrastructure, not a chat upgrade, so it stays off until a profile actually ships reports.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What dsh-research-report does

Immutable evidence tiles flow through verification nodes into a hash-sealed report block.

dsh-research-report is a DeepSeek Harness plugin that produces research reports with an auditable evidence trail and a recomputable integrity seal. DeepSeek Harness can use the plugin’s retrieval orchestration through the ctx.web and ctx.jobs seams: web providers may capture or gather URLs, while jobs may assemble reports in the background. The plugin stores immutable evidence snapshots in a content-addressed ledger at <ledgerRoot>/objects/<sha256>, with JSONL journals. Each claim records the evidence IDs it relies on, and each verification re-reads the snapshots and checks quoted text and numbers byte for byte.

A sealed report is written under <reportRoot>/<slug(topic)>/<YYYYMMDD-HHmmss>/. Its report.md, manifest.json, verification.jsonl, and disconfirmation.jsonl preserve the report, evidence hashes, audit-journal hashes, and verification results. The manifest’s SHA-256 hash seals the directory. Before sealing, every bound claim is re-audited offline; changed verdicts, missing or altered evidence, and journal-serialisation failures block the seal.

This suits agents that need reproducible, inspectable research rather than an unstructured answer. It is not a semantic fact checker: verification is based on literal byte-level matches, not meaning or embeddings. It also requires the DeepSeek Harness 0.2.x-compatible plugin environment, Node ^22.19.0 || >=24.0.0, and ESM; ctx.web and ctx.jobs integrations are optional. Dataset citation cross-checking additionally needs dsh-data-quality.

dsh-research-report documentation

How dsh-research-report works

DeepSeek Harness loads the plugin into a profile and provides the ctx.web and ctx.jobs seams that the plugin can reuse. Optional ctx.web providers capture or gather URLs, and optional ctx.jobs support background report assembly. The plugin’s durable state is separate from the session log: the ledger stores immutable snapshots at <ledgerRoot>/objects/<sha256> and records operations in JSONL journals.

Claims are bound to evidence IDs. On verification, the plugin recomputes each snapshot hash and checks every quoted span and number for a byte-level match. A claim with no bound evidence or no checkable literal is unverified; evidence that cannot confirm or deny the literals is insufficient; an absent claimed value is disproven; and missing or tampered snapshots are contradicted. Verdicts are journaled, with the latest verdict taking precedence.

dsh-research-report reports and files

DeepSeek Harness receives a versioned report under <reportRoot>/<slug(topic)>/<YYYYMMDD-HHmmss>/. The directory contains:

  • report.md
  • manifest.json
  • verification.jsonl
  • disconfirmation.jsonl

The SHA-256 seal is computed from manifest.json. That manifest includes the report hash, every evidence hash, and the hash of each audit journal. Before sealing, the plugin re-verifies all bound claims offline. Verdict drift, altered or missing evidence, or a journal serialisation failure prevents sealing.

Requirements for dsh-research-report

DeepSeek Harness compatibility is documented for dsh-v0.2.1-alpha.1; the declared peer ranges are >=0.1.6-0 <0.2.0 || >=0.1.7-0 <0.2.0. The plugin requires Node ^22.19.0 || >=24.0.0 and ESM. Peer dependencies include @deepseek-ai/cordis, @deepseek-ai/schemastery, @deepseek-ai/dsh-session, @deepseek-ai/dsh-tools, @deepseek-ai/dsh-system-prompt, @deepseek-ai/dsh-web, and @deepseek-ai/dsh-jobs. The README does not specify configuration keys or default values.

Commands and optional integrations

DeepSeek Harness can verify that the profile row is mounted with dsh --profile demo --dump-config | grep dsh-research-report. The README documents removal with dsh plugin --profile demo remove dsh-research-report. DOI evidence is checked without network access. If ctx.dataQuality is mounted, dsh-data-quality can cross-check CSV or JSON citations through verifyCitations; requireJournalMetadata can require journal and year metadata for academic DOI evidence.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to dsh-research-report

dsh-loopx-plugin

huangruiteng

6.7k

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePythonyesterday

AI review

dsh-loopx-plugin

What it is — DeepSeek Harness plugin that bootstraps LoopX CLI and integrates skills.

Who it is for — For managing long-horizon agent tasks using DeepSeek Harness, it adds state management. Users running agent tasks on non-DeepSeek Harness frameworks won't need this plugin.

Watch out — No obvious issues identified. Static checks show it will execute shell commands. Sandbox testing has not been conducted.

The verdict — I would install it because it enables long-horizon state management on DeepSeek Harness, but only for tasks requiring bounded loop continuation.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source
6.4k

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython3d ago

AI review

dsh-plugin

What it is — This DSH plugin mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DeepSeek Harness.

Who it is for — Users performing workflow tasks in DeepSeek Harness benefit from this plugin. People who do not need to mount external Agent OS via DSH MCP do not need this plugin.

Watch out — It is a subdirectory plugin with no single install command. It will execute shell commands. No sandbox testing was performed; no obvious pitfalls found.

The verdict — I would install it because it integrates Ouroboros directly for DeepSeek Harness.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

dsh-loopx-plugin

loopx-project

6.3k

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython1mo ago

AI review

dsh-loopx-plugin

What it is — The dsh-loopx-plugin provides a LoopX control plane for DeepSeek Harness, managing durable goals, todos, evidence, and handoffs for long-horizon agents.

Who it is for — When building coding or research agents with DeepSeek Harness that require cross-session Goal and Todo state, this plugin can be installed. For users who only need single-session instant task completion, the durable state management provided by this plugin falls outside their requirements.

Watch out — No obvious issues found. From source installation, the build script requires manual approval to execute.

The verdict — I would install it because it maintains a bounded loop GoalBar for DeepSeek Harness agents, which is necessary for long-horizon work.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source
3.5k

Embeds the active installed Codex Taskboard runtime in the DeepSeek Harness sidebar, using its launcher runtime descriptor instead of a fixed port.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceJavaScript7d ago

AI review

deepseek-harness

What it is — Integrates Codex Taskboard runtime into DeepSeek Harness sidebar.

Who it is for — Users who embed Codex Taskboard into DeepSeek Harness sidebar are suitable to install this plugin. Users who do not want to provide an API key or token are not suitable to install it, because it requires providing one.

Watch out — No sandbox testing was performed. It requires providing an API key or token and may execute shell commands. No obvious issues found.

The verdict — I would not install it because there is no single command to install it.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Source

Installs a dedicated AI novel-writing preset and workbench: revisioned local project assets, a compact side drawer, and native approval-gated single-file changes.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceTypeScript3d ago

AI review

dsh-ai-novel-writer

What it is — Adds an AI novel-writing preset and workbench to DeepSeek Harness.

Who it is for — Users who are writing long novels in DeepSeek Harness and want AI assistance for chapter generation with manual review are suitable for installing it. Users who require automated batch generation or integration with mature editors should not, as it only supports a minimal manual review workflow.

Watch out — No obvious issues found. This is an early MVP version with capabilities only about 10% of the desktop version. It only supports the minimal creation chain with manual approval.

The verdict — I would not install it, because it lacks the full project tree and batch workflows of the desktop version.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
Source

dsh-agent-teams

NanmiCoder

2.2k

AgentTeams multi-agent teams.

Installed cleanly when we ran it

npm packageJavaScript1mo ago

AI review

dsh-agent-teams

What it is — Turns the current DeepSeek Harness session into a captain runtime: continuable sub-agents, a dependency-aware task state machine, direct member mailboxes, and a live Web activity panel.

Who it is for — You are in DeepSeek Harness splitting one goal into dependency-ordered tasks for continuable sub-agents, and you want the Web panel for the task DAG and member progress. Do not install if that same session must keep writing the implementation: the plugin parks it in the captain seat—create the team, assign, consolidate.

Watch out — The recommended host is still DeepSeek Harness 0.2.1-rc.2, an RC; 0.1.25 exists to stop that host from rejecting the install. The plugin executes shell commands. Opt-in quality gates audit at completion and do not intercept host writes. A fresh-profile sandbox install registered with the harness; the desktop app ships its own core, so upgrading the global CLI does not move it.

The verdict — Worth it only if staging a roster and DAG first is acceptable—scheduling does not start until Approve & Run.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details