deepscientist-codex
v0.1.0Native Codex CLI adapter for DeepScientist research semantics: quest state, memory, artifacts, baselines, experiments, paper workflows, and formal evidence provenance. Codex-native tools still handle routine file, shell, Git, test, build, and process work.
By DeepScientist Hermes adaptation2 GitHub starsUpdated 5 months ago
Directory evidence
- Runtimes
- Codex
- Parsed components
- 21 skill or MCP entries
- Source updated
- May 6, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install deepscientist-codex for Codex
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add deepscientist-codex@agent-plugin-marketplacePaste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/Rycen7822/DeepScientist-hermesClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is DeepScientist-codex/.
Plugin files
├── .codex-plugin/plugin.json├── skills/deepscientist-analysis-campaign/SKILL.md├── skills/deepscientist-baseline/SKILL.md├── skills/deepscientist-codex/SKILL.md├── skills/deepscientist-decision/SKILL.md├── skills/deepscientist-experiment/SKILL.md├── skills/deepscientist-experiment-execution/SKILL.md├── skills/deepscientist-figure-polish/SKILL.md├── skills/deepscientist-finalize/SKILL.md├── skills/deepscientist-idea/SKILL.md├── skills/deepscientist-intake-audit/SKILL.md├── skills/deepscientist-optimize/SKILL.md├── skills/deepscientist-paper-fetch/SKILL.md├── skills/deepscientist-paper-reliability-verification/SKILL.md├── skills/deepscientist-paper-reliability-verifier/SKILL.md├── skills/deepscientist-quest-handoffs/SKILL.md├── skills/deepscientist-rebuttal/SKILL.md├── skills/deepscientist-review/SKILL.md├── skills/deepscientist-scout/SKILL.md├── skills/deepscientist-strict-research/SKILL.md├── skills/deepscientist-write/SKILL.md└── skills/deepscientist-writing-plans/SKILL.md
Included Skills21
Use when a quest needs one or more follow-up runs such as ablations, robustness checks, error analysis, or failure analysis after a main experiment.
Use when a quest needs to attach, import, reproduce, repair, verify, compare, or publish a baseline and its metrics.
Use DeepScientist from Codex CLI through the native dsctl adapter for research semantics/provenance: quests, memory, artifacts, experiments, strict literature workflow, paper/resource operations, and formal ds_bash_exec evidence. Routine file/search/edit, shell, Git, tests/builds, and process work remains Codex-native. This adapter is not MCP and does not call external ds.
Use when the quest needs an explicit go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition with reasons and evidence.
Use when a quest is ready for a concrete implementation pass or a main experiment run tied to a selected idea and an accepted baseline.
Execute DeepScientist quest experiment command documents with durable ds_* logging, manifest validation, and cautious baseline-gate handling.
Use when a quest needs a polished milestone chart, paper-facing figure, appendix figure, or a mandatory render-inspect-revise pass before treating a figure as final.
Use when the quest is ready to consolidate final claims, limitations, recommendations, summary state, and graph exports before stopping or archiving.
Use when a quest needs concrete hypotheses, limitation analysis, candidate directions, or a selected idea relative to the active baseline.
Use when a quest does not start from a blank state and the agent must first audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials before choosing the next anchor.
Use when an algorithm-first quest should manage candidate briefs, optimization frontier, branch promotion, or fusion-aware search instead of the paper-oriented default loop.
Use when a DeepScientist quest needs quest-local paper retrieval, arXiv/OpenReview PDF reading, or official resource verification without clipping into llm-wiki.
Verify paper reliability through the bundled DeepScientist verifier workflow before using papers as evidence.
Verify scholarly-paper reliability for AI-scientist agents by checking citation counts, venue level, journal level, publication type, and retraction/update status.
Create durable DeepScientist quest handoff documents, AGENTS.md files, researcher packages, and verified sync artifacts.
Use when a quest already has a paper, draft, or review package and the task is to map reviewer feedback into experiments, manuscript deltas, and a durable rebuttal / revision response.
Run a skeptical evidence-grounded DeepScientist review pass for drafts, paper-like reports, claim scope, and follow-up routing.
Use when a quest needs problem framing, literature scouting, dataset or metric clarification, or baseline discovery before deeper work.
Strict literature research mode for DeepScientist quests: broad candidate scouting first, reliability verification, conservative filtering, quest-local PDF download, then iterative bibliography reading notes before answering/writing.
Use when a quest has enough evidence to draft or refine a paper, report, or research summary without inventing missing support.
Write DeepScientist-aware implementation, experiment-roadmap, code-only, and formal-command plans with TDD and durable quest outputs.
Plugin manifests1
{
"name": "deepscientist-codex",
"version": "0.1.0",
"description": "Native Codex CLI adapter for DeepScientist research semantics: quest state, memory, artifacts, baselines, experiments, paper workflows, and formal evidence provenance. Codex-native tools still handle routine file, shell, Git, test, build, and process work.",
"author": {
"name": "DeepScientist Hermes adaptation"
},
"skills": "./skills",
"interface": {
"displayName": "DeepScientist Codex Native",
"shortDescription": "Use DeepScientist research state from Codex CLI while leaving routine coding operations to Codex-native tools.",
"longDescription": "A self-contained Codex CLI plugin that embeds the retained headless DeepScientist runtime. It exposes project-local quest, memory, artifact, baseline, paper, analysis, and formal experiment provenance through scripts/dsctl.py, while ordinary file editing/search, shell, Git, tests, builds, and process management remain Codex-native responsibilities.",
"developerName": "DeepScientist Hermes adaptation",
"category": "Productivity",
"capabilities": [
"Read",
"Write"
],
"defaultPrompt": [
"Use DeepScientist Codex Native only for DeepScientist research semantics: quest state, durable user requirements, memory, artifacts, baselines, experiment records, paper/reliability workflows, analysis campaign state, and formal evidence provenance. Use Codex-native file/search/edit/shell/Git/test/build/process capabilities for routine operation-layer work. Treat ds_bash_exec as a provenance tool for formal experiment, baseline, analysis, or paper-facing commands, not as a general shell replacement. Load the deepscientist-codex skill first, then load bundled support skills only when the subtask needs them. Keep the native Codex transport boundary and do not reintroduce protocol-server transport."
],
"brandColor": "#4D6A7A"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[deepscientist-codex on Agent Plugins Marketplace](https://pluginsmp.com/plugins/deepscientist-codex)