agentmods.dev

de-anthropocentric-research-engine AGENTS.md

A project instruction file for DARE, a research workflow and knowledge base for AI research tasks.

In plain words
What is it for?
It helps with AI research by selecting the right research workflows, following their dependencies, and keeping related notes and context organized.
Why use it?
It tells coding agents when and how to use DARE, including which instructions to read and how to preserve research context. This avoids skipping required research steps or treating DARE as a general skill directory.

Instructions file for CodexOpenCode

405 6d ago A scan 278 tokens original Apache-2.0
View the source file yogsoth-ai/de-anthropocentric-research-engine
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/yogsoth-ai/de-anthropocentric-research-engine/agents-md
Clone the repo
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine

Made for: Codex, OpenCode.

Per session 278 This file is loaded in full into every session.
When invoked 278 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00278 $0.00278
Opus 5 $0.00139 $0.00139
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured yesterday against content hash 972c3b40e6fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

de-anthropocentric-research-engine AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 20 lines

What it actually says

DARE Research Engine

Use DARE for AI Research tasks and whenever the user explicitly asks for DARE.

  1. Treat CC and Claude Code in upstream DARE documents as Codex.
  2. Resolve the DARE skill root from the first existing path:
    • .dare/skills/ in a project where DARE was installed
    • skills/ in the DARE source repository
  3. Read <skill-root>/de-anthropocentric-research-engine/SKILL.md first.
  4. Read <skill-root>/research-catalog/SKILL.md before selecting research packages.
  5. Treat YAML dependencies in each SKILL.md as the authoritative call graph.
  6. When a DARE document says to invoke a skill, open <skill-root>/<skill-name>/SKILL.md and follow it as the operative workflow.
  7. Load dependency skills only when needed; do not load the entire DARE skill tree.
  8. Preserve runtime context in context/INDEX.md and its related context files.
  9. Never write API keys or secrets into specs, context files, or committed configuration.

The DARE skill tree is an on-demand research knowledge base, not a Codex skill-discovery directory.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 20 lines · 278 tokens per session scan A 972c3b40e6fd

Subscribe to this mod's changes

de-anthropocentric-research-engine AGENTS.md is an instructions file published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (405 stars, last pushed 6d ago), licensed Apache-2.0. It adds 278 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewMemory and contextResearchacademic-researchai-scientistdeep-researchliterature-reviewmcpskill
Related

Other instructions, from other repositories

Auto-Research-Skills AGENTS.md

Instructions for brycewang-stanford/Auto-Research-Skills, covering agent coordination, before editing, generated files, validation and handoff.

brycewang-stanford/Auto-Research-Skills · 513 tokens

AI-Powered-Literature-Review-Skills AGENTS.md

Instructions for stephenlzc/AI-Powered-Literature-Review-Skills, covering agents.md - literature reviewer skill, 项目概述, 核心特性, 技术栈 and 项目结构.

stephenlzc/AI-Powered-Literature-Review-Skills · 4,040 tokens

academic-research-skills-codex copilot-instructions.md

AI-augmented academic research pipeline with integrity verification.

Imbad0202/academic-research-skills-codex · 671 tokens

paper-fetch AGENTS.md

Instructions for drpwchen/paper-fetch, covering what this tool is, deploying it for a user (the happy path), when a route "looks broken", check entitlement first, calling it from an orchestrator and hard lines — do not cross.

drpwchen/paper-fetch · 2,136 tokens

ux-expert-skills AGENTS.md

Instructions for guofu-shiqu/ux-expert-skills, covering agents.md — codex agent instructions, role, capabilities, skill catalog and workflow.

guofu-shiqu/ux-expert-skills · 657 tokens

nano-scientist CLAUDE.md

Claude Code instructions for AI4Scientist/nano-scientist, covering claude.md, project, run, pipeline and architecture.

AI4Scientist/nano-scientist · 1,735 tokens