research

research is a skill for Claude Code, Codex from aethrox/doctrine. It costs 58 tokens per session (1,049 once invoked), scanned A, original, MIT.

A research workflow that investigates technical questions using original sources such as official documentation, source code, standards, and first-party API responses, then saves cited findings in the project.

In plain words
What is it for?
Use it to verify technical claims, gather documentation or API facts, and produce a cited research file for later use.
Why use it?
It helps prevent decisions based on summaries or blog posts that may misstate the original facts. Each finding can be traced back to the source that owns it.

Skill for Claude CodeCodex

Part of the doctrine plugin — 33 skills shipped together

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 skills/aethrox/doctrine/research
Any agent
npx skills add aethrox/doctrine --skill research
Clone the repo
git clone --depth 1 https://github.com/aethrox/doctrine

Made for: Claude Code, Codex.

Or install doctrine, the plugin that ships this one along with the rest of its 33 skills.

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 research

README.md
[![agentmods](https://agentmods.dev/badge/skills/aethrox/doctrine/research.svg)](https://agentmods.dev/skills/aethrox/doctrine/research)
Your own site
<a href="https://agentmods.dev/skills/aethrox/doctrine/research"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,049 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00058 $0.01049
Opus 5 $0.00029 $0.00524
Sonnet 5 $0.00012 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured 4d ago against content hash 5c634728f595, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d ago.

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/research/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research

A claim is only as good as the source it traces back to. This skill's defining constraint: every finding in the output must be traceable to the primary source that actually owns the fact (official docs, source code, a spec, a first-party API response), not to a blog post, forum answer, or summary that itself read the primary source once. If tracing stops at a secondary source, that's stated as a limitation, not hidden.

Phase 1: Scope the question

State the specific question or claim being investigated, narrowly enough that "found" and "not found" are both clear outcomes. A vague scope ("research React") produces an unfalsifiable report; a narrow one ("does React's useEffect cleanup run before or after the next effect's setup, per the official docs") produces a checkable answer. If the request bundles several questions, split it, mixing them is how one weak answer contaminates the credibility of the rest.

Phase 2: Trace every claim to its primary source

For each sub-question:

  1. Go to the source that owns the fact. Official documentation, the actual source code, a published spec or RFC, a first-party API response, not a secondary write-up of any of these.
  2. If only a secondary source turns up, follow its own citation back. A blog post that says "per the docs, X" is a pointer, not the finding; open what it points to and verify the docs actually say X before citing the docs, not the post.
  3. If tracing dead-ends at a secondary source (the primary source is gone, paywalled, or the secondary source cites nothing verifiable), say so explicitly in the finding rather than presenting a secondary source as if it were primary.
  4. Note the primary source's own date or version. A fact that was true in an old version of a doc or API may not be true now; carry the version/date forward into the finding, not just the claim.

Phase 3: Weigh source credibility

Where more than one primary-adjacent source disagrees, or where authority isn't obvious, check the source against the CRAAP criteria (Currency, Relevance, Authority, Accuracy, Purpose; the standard library-science checklist for source evaluation):

Read the full file on GitHub · 55 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 55 lines · 58 tokens per session scan A 5c634728f595

Subscribe to this mod's changes

research is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 23d ago), licensed MIT. It adds 58 tokens to every session and 1,049 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

planning-and-task-breakdown

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

shashankswe2020-ux/whoop-mcp · 56 tokens

qa-knowledge

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

griddynamics/rosetta · 32 tokens

ue-mcp-epic-routing

Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.

db-lyon/ue-mcp · 81 tokens