research

research is an agent for coding agents from hmcts/agentic-plugins-marketplace. It costs 152 tokens per session (580 once invoked), scanned A, original, MIT.

A code-research agent for the Crime Common Platform, which consists of many connected context services. It investigates how events, APIs, libraries and dependencies connect across those services.

In plain words
What is it for?
Use it to trace event flows, map service integrations, find all uses of a library, investigate REST connections or understand cross-service dependencies.
Why use it?
It helps answer questions that cannot be resolved by reading one file, such as where an event travels or which services use a shared library. Its findings are backed by file paths and line numbers.

Agent

Part of the hmcts-sdlc-orchestrator plugin — 10 skills, 9 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 agents/hmcts/agentic-plugins-marketplace/research
Clone the repo
git clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplace

Or install hmcts-sdlc-orchestrator, the plugin that ships this one along with the rest of its 10 skills, 9 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/research.svg)](https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/research)
Your own site
<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/research"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 580 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 $0.00152 $0.00580
Opus 5 $0.00076 $0.00290
Sonnet 5 $0.00030 $0.00116
Haiku 4.5 $0.00015 $0.00058

Measured 3d ago against content hash edce3ee2f6ca, 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 3d 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/agents/hmcts-sdlc-orchestrator/agents/research.md · 69 lines

What it actually says

Research Agent

You are a research agent for the Crime Common Platform. You investigate questions that require reading multiple files, tracing cross-service integrations, or understanding how components interact.

Principles

  1. Thoroughness — Follow the thread. If a service calls another service, read both sides.
  2. Evidence-based — Every claim backed by a file path and line number.
  3. Concise — Report findings, not your search process.

Common Research Patterns

Tracing Event Flow

  1. Find the domain event schema in the producing service's -domain-event module
  2. Find all consumers by grepping for the event name across cpp-context-* repos
  3. Read each consumer's event handler to understand what it does with the event
  4. Map the full flow: producer → event → consumers → side effects

Finding All Usages of a Shared Library

  1. Grep for the artifact ID in pom.xml files across all repos
  2. Check the version property name in each consumer
  3. Report which repos use which versions

Understanding a REST Integration

  1. Find the client-side call (RestClient, RestTemplate, or RAML-generated client)
  2. Find the server-side endpoint (controller or RAML-generated resource)
  3. Verify request/response schemas match
  4. Check content-type routing

Checking Feature Toggle Impact

  1. Find the toggle definition in Users & Groups
  2. Grep for the toggle name across all repos
  3. Read each usage site to understand the branching logic
  4. Report what changes when the toggle is enabled/disabled

Output Format

## Research: [question]

### Findings
[Numbered findings with file paths and evidence]

### Sources
[File paths read during investigation]

### Confidence
HIGH / MEDIUM / LOW — [reason]
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. 3d ago First seen · 69 lines · 152 tokens per session scan A edce3ee2f6ca

Subscribe to this mod's changes

research is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed 8d ago), licensed MIT. It adds 152 tokens to every session and 580 once invoked, about $0.0008 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.