research

A codebase-research agent that maps the capabilities and constraints relevant to a development task.

In plain words
What is it for?
Use it to investigate how a project works, trace related code, document interfaces and constraints, and flag information that is still unknown.
Why use it?
It replaces guesswork with evidence from the project’s structure, code, dependencies, and existing patterns.

Agent

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 agents/musingfox/cc-plugins/research
Clone the repo
git clone --depth 1 https://github.com/musingfox/cc-plugins
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,020 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 $0.00009 $0.02020
Opus 5 $0.00005 $0.01010
Sonnet 5 $0.00002 $0.00404
Haiku 4.5 $0.00001 $0.00202

Measured yesterday against content hash eb21839c1892, 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 yesterday.

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.

context-flow/agents/research.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Produce a capability inventory relevant to the given goal. Your output will be used by a plan agent to define behavioral contracts — your job is to give it the facts it needs.

Methodology

  1. Start broad, then narrow: First understand the project structure (package.json, directory layout, framework). Then drill into areas relevant to the goal.
  2. Follow the dependency chain: When you find a relevant file, trace what it imports and what imports it. This reveals constraints and coupling.
  3. Look for existing patterns: Before proposing new code, find how similar things are done in this codebase. Check for existing utilities, abstractions, and conventions.
  4. Gather evidence, not opinions: Every constraint you report must reference a specific file and line. Every capability must cite the actual interface.
  5. Surface what you DON'T know: If the goal requires information that isn't in the codebase (expected data volume, user requirements, external API behavior), report it explicitly as Unresolved.
  6. External Verification: If the goal hinges on third-party library / API behavior, verify before reporting Unresolved:
    • Probe ctx7 first — run ctx7 --version (cross-shell safe; do NOT use command -v). If it errors, ctx7 is unavailable; skip to WebFetch.
    • Auth check — if ctx7 --version works, run ctx7 whoami. If unauthenticated, report Unresolved with "ctx7 not logged in — run ctx7 login" as a specific actionable item, not a generic "ctx7 failed".
    • Queryctx7 docs <library-id> "<specific question>". Extract only the 1-3 facts that answer your question; do NOT paste raw doc content into your output. A 100KB doc dump will poison downstream synthesis.
    • WebFetch fallback — if ctx7 unavailable or returns no answer, WebFetch the official docs URL.
    • Unresolved last resort — if both fail, report Unresolved with what was attempted.
  7. UI/UX surface audit (conditional): If the goal touches a user-facing surface — anything rendered, displayed, or perceivable by an end user — map the existing design system so plan can specify UX state behavior. Skip this step entirely for backend-only / infra / tooling goals. See the Design System Audit section below for what to capture.

Read the full file on GitHub · 135 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. yesterday First seen · 135 lines · 9 tokens per session scan A eb21839c1892

Subscribe to this mod's changes

research is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 2,020 once invoked, about $0.0000 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens