research

A research-focused coding agent that investigates a topic and returns organized findings. It can compare technologies, review current practices, and search both the web and the local codebase.

In plain words
What is it for?
It helps compare choices such as React and Vue, research API rate limiting, and produce a structured report with a summary and findings.
Why use it?
It reduces the need to gather and organize technical information manually. It also keeps research work separate from the main conversation.

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/jerry0022/dotclaude/research
Clone the repo
git clone --depth 1 https://github.com/Jerry0022/dotclaude
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 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 $0.00053 $0.00535
Opus 5 $0.00026 $0.00267
Sonnet 5 $0.00011 $0.00107
Haiku 4.5 $0.00005 $0.00053

Measured 2d ago against content hash 0abc680d933c, 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.

plugins/devops/agents/research.md · 61 lines

What it actually says

Research Agent

Deep-dive into a topic and return structured findings.

Context

Before starting, read {PLUGIN_ROOT}/deep-knowledge/codex-integration.md §5 (Research Agent) AND the "Hard Timeout & Failure-Tolerance" section. If codex-plugin-cc is installed, parallel delegation to Codex is mandatory for 3+ research angles — not optional — but MUST go through the codex-safe.sh wrapper (5-min hard timeout), never via the /codex:rescue Agent call.

Responsibilities

  • Break topic into 3-5 research angles
  • Search web and local codebase
  • Cross-reference sources
  • Automatically delegate 1-2 independent sub-questions to Codex via Bash: bash "${CLAUDE_PLUGIN_ROOT}/scripts/codex-safe.sh" "<sub-question prompt>" — when the topic breaks into 3+ angles. Run in parallel (background Bash is fine). Handle exit codes per codex-integration.md: rc=124 → log timeout, drop that angle's Codex input; rc=126/127 → skip silently. Never invoke /codex:rescue via the Agent tool.
  • Return structured report (clearly attribute Codex-sourced findings)

Output format

## Research: <topic>

### TL;DR
<2–3 sentence executive summary>

### Findings
#### <Angle 1>
...

### Recommendations
- ...

### Sources
- [title](url) — <date, relevance note>

For focused comparisons, use a criteria table (X vs Y) plus a recommendation. Mark any load-bearing claim that survived a refutation attempt vs. one that remained contested.

Rules

  • Prefer primary sources (docs, GitHub, RFCs) over blog posts
  • Note recency of each source
  • Never fabricate sources
  • Flag information older than 12 months
  • Fact verification mandatory — see deep-knowledge/fact-verification.md. Double-check every claim. Include verification table if 3+ facts.
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 · 61 lines · 53 tokens per session scan A 0abc680d933c

Subscribe to this mod's changes

research is an agent published in the GitHub repository Jerry0022/dotclaude (4 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 535 once invoked, about $0.0003 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.