A research workflow for investigating a question using multiple sources and producing a cited Markdown report under docs/research/.

Use it for general research, market or competitor analysis, and technology selection when comparing tools, libraries, frameworks, software kits, or repositories.

It separates short lookups from deeper investigations and provides evidence that readers can check.

research — Skill for Claude Code and Codex by int2t05: A research workflow for investigating a question using multiple…

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add int2t05/engineering-skills

Claude Code

/plugin install engineering-skills

Made for: Claude Code, Codex.

Or install engineering-skills, the plugin that ships this one along with the rest of its 48 skills, 1 agent, 1 hook.

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/int2t05/engineering-skills/research.svg)](https://agentmods.dev/skills/int2t05/engineering-skills/research)

Your own site

<a href="https://agentmods.dev/skills/int2t05/engineering-skills/research"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/research.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,521 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.02521
Opus 5	$0.00000	$0.01260
Sonnet 5	$0.00000	$0.00504
Haiku 4.5	$0.00000	$0.00252

Measured 5d ago against content hash 405563e2356c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 5d 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/02-research/research/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research

Source-backed investigation that produces a cited Markdown artifact under docs/research/. Three modes share one spine — frame the question, search with the mode's source strategy, adversarially verify, synthesize a cited report — but differ in sources, frameworks, and output template.

When to use

general — deep multi-source web research with inline citations (深度调研, 调研转文档)
market — market sizing, competitor analysis, investor due diligence, industry intelligence (市场调研, 竞品分析)
tech-selection — choosing/comparing a stack, library, framework, or repo for a concrete requirement (技术选型, 方案对比, 选哪个)
Triggers on "deep research", "调研报告", "市场调研", "竞品分析", "技术选型", "选哪个", "方案对比"

Not for: short queries or single-source lookups; design visual references (use design-research); writing the PRD/spec itself (use spec). Does not build embeddings, vector stores, or persistent indexes.

Steps

1. Pick the mode and frame the question

Route by the dominant signal in the ask — don't guess:

Signal in the ask	Mode	Source strategy
Tech / framework / library / SDK / repo / tool comparison	tech-selection	GitHub-first P0
Market / competitor / investor / industry / pricing / TAM	market	SEC, reports, press
Everything else — concept, spec, state-of-the-art survey	general	Official docs, blog, paper, GitHub

If the ask hits two or more modes (e.g. "research DeepSeek's harness" is both a tech-framework question and a company deep-dive; "an AI company's stack + market" is both tech-selection and market), ask the user to pick one — "技术选型（GitHub 源优先）/ 市场分析 / 通用深度？三选一" — rather than silently choosing. A single dominant signal needs no question; state assumptions and proceed.

Then restate the goal, scope, output language, and output path:

general → docs/research/YYYY-MM-DD-<slug>.md (slug: 2-4 words, lowercase ASCII; transliterate non-ASCII; no redundant prefixes). If the file exists, append -2 or -HHmmss; overwrite only with explicit permission.
market → docs/research/market.md
tech-selection → docs/research/competitor.md

Read the full file on GitHub · 137 lines

Files

What ships with it

9 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.

5d ago First seen · 137 lines · 0 tokens per session scan A 405563e2356c

Subscribe to this mod's changes

research is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,521 tokens. 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 2026-08-31.

Code review Research Writing and docs agent-skills claude-code claude-code-plugin sdlc

incident-response

Protocolo de respuesta ante incidentes en produccion: triaje, mitigacion, causa raiz y postmortem. Usar ante caidas, errores criticos, incidentes de seguridad o degradacion de servicio.

686f6c61/alfred-dev · 49 tokens

pr-workflow

Crear pull requests completas con descripcion, labels y reviewers.

686f6c61/alfred-dev · 14 tokens

compliance-check

Usar para verificar cumplimiento RGPD, NIS2 y CRA. También: verificar RGPD, cumplimiento normativo, NIS2, CRA, Cyber Resilience Act, protección de datos, regulación europea.

686f6c61/alfred-dev · 46 tokens

threat-model

Usar para modelar amenazas con metodología STRIDE. También: análisis de amenazas, STRIDE, superficie de ataque, vectores de ataque, modelado de amenazas.

686f6c61/alfred-dev · 38 tokens

sbom-generate

Usar para generar Software Bill of Materials para cumplimiento del CRA. También: Software Bill of Materials, inventario de componentes, CycloneDX, SPDX, cadena de suministro.

686f6c61/alfred-dev · 40 tokens

memory

This skill should be used when the user asks to record a design decision, search past project decisions, inspect the Alfred memory timeline, or work with the alfred-memory MCP server. Use it to call the namespaced MCP tools instead of inventing history.

686f6c61/alfred-dev · 53 tokens