agentmods.dev

argo-deep-research

argo-deep-research is a skill for Claude Code, Codex from taxueseek/argo. It costs 50 tokens per session (395 once invoked), scanned A, original, Apache-2.0.

A research skill that builds evidence dossiers from multiple sources and checks important facts and numbers against source pages. It can search academic databases such as arXiv, PubMed, and Semantic Scholar and assess source credibility.

In plain words
What is it for?
Use it for multi-source research, academic literature reviews, fact and number verification, research planning, and evidence-quality checks.
Why use it?
It reduces unsupported claims and weak evidence when a question needs more than a single web search, especially for high-stakes facts or numerical claims.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/research.py "<topic>" --depth deep --json.

not rated 264repo +27 2d ago A scan 50 tokens original Apache-2.0

Good fit Use it for multi-source research, academic literature reviews, fact and number verification, research planning, and evidence-quality checks.

Compare 6 skills from other repositories ↓
View source ↗ taxueseek/argo
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/taxueseek/argo
agentmods
npx agentmods add skills/taxueseek/argo/argo-deep-research

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for argo-deep-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/taxueseek/argo/argo-deep-research/github.svg)](https://agentmods.dev/skills/taxueseek/argo/argo-deep-research)
Your own site
<a href="https://agentmods.dev/skills/taxueseek/argo/argo-deep-research"><img src="https://agentmods.dev/badge/skills/taxueseek/argo/argo-deep-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for argo-deep-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/taxueseek/argo/argo-deep-research"><img src="https://agentmods.dev/badge/skills/taxueseek/argo/argo-deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.00395
Opus 5.5 $0.00020 $0.00158
Sonnet 5.5 $0.00010 $0.00079
Haiku 4.5 $0.00005 $0.00040

Measured yesterday against content hash b2a15517b549, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

argo-deep-research 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.

skills/argo-deep-research/SKILL.md · 39 lines

What it actually says

Argo Deep Research & Fact Verification

Use this skill when a question requires multi-source evidence gathering, academic literature synthesis, or strict fact/number verification rather than a single web search.

Core Workflow

  1. Generate a research dossier (sources, coverage, gaps, quality gates): 
    python3 scripts/research.py "<topic>" --depth deep --json
    Or pass structured work packages: 
    python3 scripts/research.py "<topic>" --work-packages '<json-or-path>' --verify 3 --json
  2. Verify high-stakes facts & numbers directly from full source pages: 
    argo search "<query>" --verify 3 --numverify 2 --json --fields agent
  3. Academic deep dive (arXiv, Semantic Scholar, OpenAlex, Crossref, PubMed; disables early-stop): 
    argo search "<topic>" --academic-deep --json --fields agent
  4. Score credibility independently: 
    echo '{"results": [...]}' | python3 scripts/evidence.py "<query>" --stdin --json --high-stakes

Discipline

  • Never treat SERP redirect URLs (baidu/s, sogou/link) or social posts as primary factual truth.
  • When fetch_required=true or quality_gate_results.passed=false, downgrade claims and cite exact source URLs.
  • See references/research-protocol.md for full dossier and work-package schemas.
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 · 39 lines · 50 tokens per session scan A b2a15517b549

Subscribe to this mod's changes

argo-deep-research is a skill published in the GitHub repository taxueseek/argo (264 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 395 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-14.

ResearchScientificacademic-searchagent-toolsai-agentdeep-researchdsh-ecosystemdsh-plugin
Related

argo-deep-research compared with skills from other repositories

argo-deep-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
argo-deep-researchtaxueseek/argoSkill2642d agoApache-2.0A50Claude Code, Codex
deep-researchLiyux3/scholar-mcpSkill8yesterdaynoneA49Claude Code, Codex
formulate-hypothesesyogsoth-ai/de-anthropocentric-research-engineSkill51222d agoApache-2.0A54Claude Code, Codex
design-experimentyogsoth-ai/de-anthropocentric-research-engineSkill51222d agoApache-2.0A36Claude Code, Codex
bias-detectionyogsoth-ai/de-anthropocentric-research-engineSkill51222d agoApache-2.0A39Claude Code, Codex
construct-causal-modelyogsoth-ai/de-anthropocentric-research-engineSkill51222d agoApache-2.0A34Claude Code, Codex
map-validity-envelopeyogsoth-ai/de-anthropocentric-research-engineSkill51222d agoApache-2.0A55Claude Code, Codex