What is elimination-research?

A structured research process for choosing among products, tools, services, or vendors using stated criteria and evidence.

Use it to collect prices, specifications, replacement costs, images, and sources, then produce datasets, comparison reports, and ownership-cost estimates.

It replaces an informal shortlist with a reproducible comparison, showing how options were scored and why they were eliminated.

elimination-research — Skill for Claude Code and Codex by glebis

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 glebis/claude-skills --skill elimination-research

Clone the repo

git clone --depth 1 https://github.com/glebis/claude-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/glebis/claude-skills/elimination-research/github.svg)](https://agentmods.dev/skills/glebis/claude-skills/elimination-research)

Your own site

<a href="https://agentmods.dev/skills/glebis/claude-skills/elimination-research"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/elimination-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/glebis/claude-skills/elimination-research"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/elimination-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,302 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.

Model	Per session	Once invoked
Fable 5.1	$0.00109	$0.01302
Opus 5	$0.00055	$0.00651
Sonnet 5	$0.00022	$0.00260
Haiku 4.5	$0.00011	$0.00130

Measured 12d ago against content hash 070e19a16d5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

elimination-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 12d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/elimination_research_lib/application/__init__.py, scripts/elimination_research_lib/application/report_generator.py, scripts/elimination_research_lib/domain/__init__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

elimination-research/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Elimination Research

Purpose

Generate a reproducible elimination-research package: a shortlist dataset, numeric scoring model, quick consumer report, full audit report, raw data JSON, source/domain audit, purchase/info links, contextual images, and ownership-cost estimates.

Use this skill to turn fuzzy "which one should I choose?" requests into a clean decision workflow with explicit criteria and inspectable data.

Workflow

Follow this sequence for new comparisons:

Read references/workflow.md for the full operating procedure.
Ask the intake questions before researching. Prefer cenno popup questions when available. Use closed choices and include a free-text comment field.
Gather candidate, source, price, spec, replacement-part, image, and evidence data.
Save all collected data into a dataset JSON matching references/dataset-schema.md.
Run scripts/generate_elimination_report.py to generate reports.
Verify the quick report and full report in a browser.
Preserve raw data and numeric tables; do not hide or discard evidence just because the quick report is simplified.

Intake Questions

Ask these at the start of a new comparison, not inside the final report:

What matters most: overall quality, lowest price, sensitive-skin/user-fit, low maintenance, or travel/portability?
What is the hard limit: budget ceiling, must-have features, excluded brands, or purchase country?
How much evidence is needed: quick consumer view, full audit report, or both?
Which source types are allowed: manufacturer, retailer, price aggregator, expert review, forum, or all with flags?

Always include a comment field for constraints that do not fit the closed choices.

Output Contract

Produce these files in the chosen output directory:

quick_report.html — consumer-facing "don't make me think" report with cards/table switch, images in context, rounded prices, links, and visible ownership summaries.
report.html — full audit report with task, criteria, scoring, raw numeric data, source/domain tables, tournament, and embedded JSON.
report.md — markdown version of the full audit report.
final_report.json — normalized report payload.
raw_research_data.json — collected dataset before rendering.
image_search_results.json — cached Google image-search output when image refresh is used.

Read the full file on GitHub · 121 lines

Files

What ships with it

13 files 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.

12d ago First seen · 121 lines · 109 tokens per session scan A 070e19a16d5a

Subscribe to this mod's changes

elimination-research is a skill published in the GitHub repository glebis/claude-skills (374 stars, last pushed 9d ago), licensed MIT. It adds 109 tokens to every session and 1,302 once invoked, about $0.0005 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.

Planning Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens