github-research

A procedure for researching code examples, technical documentation, and established practices in public repositories and library documentation.

In plain words
What is it for?
Use it before building unfamiliar integrations, working with new libraries, or checking how real projects use an API or framework.
Why use it?
It helps when the technology or integration is unfamiliar or the available knowledge may be outdated, while avoiding unnecessary external research for well-known topics.

Skill for Claude CodeCodex

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/romiluz13/cc-teams/github-research
Any agent
npx skills add romiluz13/cc-teams --skill github-research
Clone the repo
git clone --depth 1 https://github.com/romiluz13/cc-teams

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,604 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 $0.00018 $0.03604
Opus 5 $0.00009 $0.01802
Sonnet 5 $0.00004 $0.00721
Haiku 4.5 $0.00002 $0.00360

Measured 2d ago against content hash 77f7dbbb670c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-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.

plugins/cc-teams/skills/github-research/SKILL.md · 448 lines

How it starts

The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.

External Code Research

Overview

Research external patterns, documentation, and best practices from GitHub and library docs when AI knowledge is insufficient. Use Octocode MCP for GitHub research, Context7 MCP for library documentation, with WebFetch as final fallback.

Core principle: Research BEFORE building, not during. External research enhances planning, not execution.

This skill is ONLY for external research. Local codebase search is handled by other CC-Teams tools (Grep/Glob/Read).

The Iron Law

NO EXTERNAL RESEARCH WITHOUT CLEAR AI KNOWLEDGE GAP OR EXPLICIT USER REQUEST

If AI training knowledge covers the technology well, skip external research - UNLESS user explicitly asks. This skill is for NEW technologies, complex integrations, unfamiliar APIs, and explicit user requests.

Rationalization Prevention

Excuse Reality
"I already know this" Check if post-2024. API may have changed.
"Research takes too long" 30s research prevents 2hr debugging.
"Docs are enough" GitHub shows real implementations, not ideal cases.
"I'll research if stuck" Research BEFORE is faster than research DURING.
"Not worth the tokens" One good pattern saves 10 bad attempts.

When to Use

ALWAYS invoke when:

  • User explicitly requests research ("research X", "how do others", "best practices", "find on github", "use octocode")
  • Technology released after 2024 (AI knowledge cutoff)
  • Complex integration patterns (auth, payments, real-time)
  • Local debugging failed 3+ times with external service errors

NEVER invoke when:

  • User says "quick" or "simple"
  • Standard patterns AI knows well (CRUD, REST, React basics)
  • Code review or refactoring tasks
  • Technology released before 2024 (unless user explicitly asks)

The rule: Trust octocode for HOW. This skill only decides WHEN.

User Confirmation Gate (REQUIRED)

BEFORE any research, ask the user:

AskUserQuestion({
  questions: [{
    question: "Do you want me to research GitHub and web for this task?",
    header: "Research?",
    options: [
      { label: "Yes, research", description: "Search GitHub code + web docs (~30s)" },
      { label: "No, skip", description: "Proceed with AI knowledge only" }
    ],
    multiSelect: false
  }]
})

Read the full file on GitHub · 448 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 · 448 lines · 18 tokens per session scan A 77f7dbbb670c

Subscribe to this mod's changes

github-research is a skill published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 3,604 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