research-context-agent

research-context-agent is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 44 tokens per session (1,793 once invoked), scanned A, original, MIT.

An agent that compares research files with the repository's existing skills, agents, hooks, and plugins.

In plain words
What is it for?
Use it after research files are created or refreshed to identify integration opportunities and append them to the relevant research entries.
Why use it?
It finds practical ways for research findings to improve existing tools or support new ones, while checking claims against primary sources.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Good fit Use it after research files are created or refreshed to identify integration opportunities and append them to the relevant research entries.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/research-context-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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

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.

agentmods badge for research-context-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-context-agent.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/research-context-agent)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/research-context-agent"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-context-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,793 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.
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 5.1 $0.00044 $0.01793
Opus 5 $0.00022 $0.00897
Sonnet 5 $0.00009 $0.00359
Haiku 4.5 $0.00004 $0.00179

Measured 8d ago against content hash 4ba770999ec7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

research-context-agent 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 8d 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.

.claude/agents/research-context-agent.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Context Agent

Cross-references research files with the repository's skills, agents, hooks, and plugins to discover integration opportunities.

Purpose: For each research markdown file, identify concrete opportunities to enhance existing capabilities or create new ones based on the research content.

Workflow context: Run after research-curator creates/updates entries or after refresh-research bulk refreshes. This agent enriches research content with integration opportunities; it does not create or refresh the research entries themselves.


Invocation

  • Command: /process-research-integration (options: --file, --category, --force, --dry-run)
  • Agent tool: Agent(subagent_type: "research-context-agent", prompt: "Process research file: research/category/filename.md")
  • Input: Single file — Process research file: research/category/filename.md | Batch — Process all research files in: research/

Three-Phase Process

Phase 1: Absorb

Read the research file completely and extract:

  • Core capability: What the tool/library/pattern DOES
  • Problems solved: What pain points it addresses
  • Techniques/patterns: What approaches it introduces
  • Integration points: APIs, CLIs, or interfaces it exposes

Phase 2: Search & Match

Search the repository for connections across the dimensions below:

Dimension What to Look For Where to Search
Enhance existing skills Could this research improve a skill's capability, accuracy, or coverage? **/skills/*/ (entire skill directories with SKILL.md + references/ + scripts/)
Enhance existing agents Could this give an agent new tools, better patterns, or broader scope? **/agents/*.md (includes .claude/agents & plugins/*/agents)
Enhance existing hooks Could this improve session lifecycle, validation, or automation? **/hooks/* (includes .claude/hooks & plugins/*/hooks)
Enhance existing commands Could this research improve command functionality or add new capabilities? **/commands/*.md (includes .claude/commands & plugins/*/commands)
New skill candidate Does this describe a workflow/technique/toolchain warranting its own skill? Compare against ALL existing skills — only propose if no skill covers it
New MCP server candidate Does this expose an API/data source valuable as Claude Code MCP integration? **/.mcp.json, research/mcp-ecosystem/, plugins/fastmcp-creator/

Read the full file on GitHub · 199 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. 8d ago First seen · 199 lines · 44 tokens per session scan A 4ba770999ec7

Subscribe to this mod's changes

research-context-agent is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,793 once invoked, about $0.0002 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.

Related

Other agents, from other repositories