research-analyze

research-analyze is a skill for Claude Code, Codex from runxhq/runx. It costs 17 tokens per session (247 once invoked), scanned A, original, Apache-2.0.

An internal research-analysis stage that evaluates only sources already admitted into a supplied evidence index. It produces a bounded research candidate with claims, supporting source digests, options, risks, and an evidence-based decision status.

In plain words
What is it for?
Use it as a verification stage inside a research workflow to assess whether a decision or public claim is supported.
Why use it?
It keeps research judgments tied to known source material and clearly separates verified facts from inference. When the supplied sources are insufficient, it says more evidence is needed.

Skill for Claude CodeCodex

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

Good fit Use it as a verification stage inside a research workflow to assess whether a decision or public claim is supported.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/analyze
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.

Any agent
npx skills add runxhq/runx --skill analyze
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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 research-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/analyze/github.svg)](https://agentmods.dev/skills/runxhq/runx/analyze)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/analyze"><img src="https://agentmods.dev/badge/skills/runxhq/runx/analyze/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 research-analyze

Your own site · 80×15
<a href="https://agentmods.dev/skills/runxhq/runx/analyze"><img src="https://agentmods.dev/badge/skills/runxhq/runx/analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 247 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00017 $0.00247
Opus 5 $0.00009 $0.00123
Sonnet 5 $0.00003 $0.00049
Haiku 4.5 $0.00002 $0.00025

Measured 8d ago against content hash 3c23e39e2331, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

research-analyze 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 8d 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/graph/analyze/SKILL.md · 32 lines

What it actually says

Research Analyze

Analyze only the supplied, runtime-admitted source index. This internal stage is shared by remote/provider evidence and native local-file evidence so acquisition cannot fork the research judgment or verification contract.

Agent task contract

research-synthesize

Preserve the objective exactly and return a bounded research_candidate with:

  • decision: ready, needs_more_evidence, or not_worth_publishing;
  • research_brief: objective, scope, concise summary, and open questions;
  • evidence_log: material claims with admitted source_digest and matching content_digest, confidence, and relevance;
  • decision_support: bounded options whose rationales cite admitted source digests;
  • risks: evidence-bound risks and uncertainty.

Distinguish verified evidence from inference. Do not browse, read other files, publish, mutate a provider, or invent source identity, delivery, certification, or settlement claims. Return needs_more_evidence when the admitted index does not support the requested decision.

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. 8d ago First seen · 32 lines · 17 tokens per session scan A 3c23e39e2331

Subscribe to this mod's changes

research-analyze is a skill published in the GitHub repository runxhq/runx (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 17 tokens to every session and 247 once invoked, about $0.0001 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 2026-09-03.