research

A research tool that searches the web and summarizes a subtopic using your LearningDNA, a set of learning preferences and instructions.

In plain words
What is it for?
Use it to research and summarize a subtopic after setting up a learning topic.
Why use it?
It keeps research tied to an existing learning topic and its configured preferences.

Skill for Claude CodeCodex

Part of the learning-dna plugin — 6 skills, 5 agents 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/avicorp/learning-dna-plugin/research
Any agent
npx skills add avicorp/learning-dna-plugin --skill research
Clone the repo
git clone --depth 1 https://github.com/avicorp/learning-dna-plugin

Made for: Claude Code, Codex.

Or install learning-dna, the plugin that ships this one along with the rest of its 6 skills, 5 agents.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 975 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 $0.00016 $0.00975
Opus 5 $0.00008 $0.00487
Sonnet 5 $0.00003 $0.00195
Haiku 4.5 $0.00002 $0.00097

Measured 2d ago against content hash fa7a0ecf2603, 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 2d 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/research — Research and Summarize a Subtopic

Usage

/learning-dna:research <topic> <subtopic>

Example: /learning-dna:research kubernetes networking

Flow

Step 1: DNA Gate (MANDATORY)

  1. Check if knowledge/LearningDNA.md exists — if missing, STOP. Do not proceed. Tell the user: "You need to set up your Learning DNA first. Run /learning-dna:new-topic <topic> to get started."
  2. Read knowledge/LearningDNA.md (global DNA)
  3. Check if knowledge/{topic}/LearningDNA.md exists (per-topic override)
  4. Merge: per-topic values override global values → use merged DNA for all content generation

Step 2: Verify Topic Exists

  • Check that knowledge/{topic}/ exists
  • If not, suggest running /learning-dna:new-topic {topic} first

Step 3: Web Research

GitHub Repo Shortcut: If the subtopic argument is a GitHub URL (https://github.com/owner/repo, github.com/owner/repo) or an owner/repo pattern, read and follow the full flow in skills/inspect-repo/SKILL.md (starting from Step 2 — the DNA gate is already done) instead of performing web research. Skip Steps 3-6 and proceed directly to Step 7.

  1. Use WebSearch to find 10-15 high-quality sources: official docs, engineering blogs, books, academic papers
  2. Present the sources to the user in a numbered list with title, URL, and brief description
  3. Wait for user approval — never auto-approve sources. Ask: "Which sources should I use? (e.g., 1,3,5-8 or 'all')"

Step 4: Fetch and Process Sources

  1. Use WebFetch on approved sources
  2. Extract key information, concepts, and examples

Step 5: Structure Content Shaped by DNA

Write markdown following these DNA-driven rules:

Content Depth:

  • Brief → 2-3 paragraphs per section, key takeaways only, bullet-point summaries
  • Standard → balanced explanation with examples
  • Detailed → thorough explanations with context and nuance
  • Comprehensive → full explanations, background theory, trade-off analysis, edge cases

Example Style:

  • Minimal → concepts only, few examples
  • Code-focused → include code samples in every section
  • Real-world scenarios → practical, production-oriented examples
  • Mixed → blend of code and real-world examples

Read the full file on GitHub · 93 lines

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. 2d ago First seen · 93 lines · 16 tokens per session scan A fa7a0ecf2603

Subscribe to this mod's changes

research is a skill published in the GitHub repository avicorp/learning-dna-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 975 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens