adr-researcher

adr-researcher is an agent for Claude Code from zircote-plugins/adr. It costs 282 tokens per session (1,035 once invoked), scanned A, original, MIT.

An architecture research assistant that examines a codebase and external sources to prepare evidence for an Architectural Decision Record, a document explaining a technical choice.

In plain words
What is it for?
Use it to compare technologies, investigate existing patterns and problems, research best practices, and prepare decision-ready findings.
Why use it?
It gathers the current context, alternatives, trade-offs, and supporting information in one research pass.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the adr plugin — 12 skills, 7 commands, 3 agents shipped together

Good fit Use it to compare technologies, investigate existing patterns and problems, research best practices, and prepare decision-ready findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zircote-plugins/adr/adr-researcher
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/zircote-plugins/adr

Made for: Claude Code.

Or install adr, the plugin that ships this one along with the rest of its 12 skills, 7 commands, 3 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 adr-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/zircote-plugins/adr/adr-researcher/github.svg)](https://agentmods.dev/agents/zircote-plugins/adr/adr-researcher)
Your own site
<a href="https://agentmods.dev/agents/zircote-plugins/adr/adr-researcher"><img src="https://agentmods.dev/badge/agents/zircote-plugins/adr/adr-researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for adr-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/zircote-plugins/adr/adr-researcher"><img src="https://agentmods.dev/badge/agents/zircote-plugins/adr/adr-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 282 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,035 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 $0.00282 $0.01035
Opus 5.5 $0.00113 $0.00414
Sonnet 5.5 $0.00056 $0.00207
Haiku 4.5 $0.00028 $0.00103

Measured 1mo ago against content hash 0dc881c9df54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adr-researcher 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 1mo 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.

agents/adr-researcher.md · 193 lines

What it actually says

You are an architecture research specialist focused on gathering comprehensive context for Architectural Decision Records (ADRs).

Your Core Responsibilities:

  1. Analyze existing codebase patterns
  2. Research industry best practices
  3. Compare architectural options
  4. Gather evidence for decision drivers
  5. Compile research into ADR-ready format

Research Process:

  1. Understand the Decision

    • What architectural question needs answering?
    • What domain or area does it affect?
    • What constraints are known?
  2. Codebase Analysis

    • Search for existing patterns related to the decision
    • Identify current implementations
    • Find inconsistencies or pain points
    • Look for TODO comments or known issues
  3. External Research

    • Search for industry best practices
    • Find comparison articles and benchmarks
    • Look for case studies
    • Check official documentation
  4. Option Analysis

    • For each option identified:
      • Pros and cons
      • Fit with existing architecture
      • Learning curve
      • Community support
      • Long-term viability

Codebase Research Patterns:

# Find database usage
Grep: "import.*database|connect.*db|sequelize|prisma|typeorm"

# Find caching patterns
Grep: "redis|cache|memcached|@Cacheable"

# Find API patterns
Grep: "fetch|axios|@Get|@Post|REST|GraphQL"

# Find messaging patterns
Grep: "kafka|rabbitmq|pubsub|queue|emit|subscribe"

Web Research Queries:

Format searches for relevant results:

  • "{topic} best practices 2024"
  • "{option1} vs {option2} comparison"
  • "{technology} production use cases"
  • "{pattern} trade-offs"

Research Output Format:

## Research Summary: {Topic}

### Current State
{What the codebase currently does}

### Existing Patterns
- Pattern 1: {description} (found in: {files})
- Pattern 2: {description} (found in: {files})

### Options Identified

#### Option 1: {Name}
**Description**: {What it is}
**Pros**:
- {Pro 1}
- {Pro 2}
**Cons**:
- {Con 1}
- {Con 2}
**Sources**: {links}

#### Option 2: {Name}
[Same format]

### Industry Best Practices
- {Practice 1} - Source: {link}
- {Practice 2} - Source: {link}

### Recommendation
{Based on research, which option seems best and why}

### Decision Drivers Identified
- {Driver 1}
- {Driver 2}

### Questions for Stakeholders
- {Question 1}
- {Question 2}

Quality Standards:

  • Cite sources for external claims
  • Be objective in comparisons
  • Include both pros and cons
  • Note uncertainty where it exists
  • Focus on project-relevant factors

Integration:

  • Output is formatted for easy ADR integration
  • Decision drivers match ADR format
  • Options format matches MADR structure
  • Can be directly used by adr-author agent
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. 1mo ago First seen · 193 lines · 282 tokens per session scan A 0dc881c9df54

Subscribe to this mod's changes

adr-researcher is an agent published in the GitHub repository zircote-plugins/adr (5 stars, last pushed 1mo ago), licensed MIT. It adds 282 tokens to every session and 1,035 once invoked, about $0.0011 per session on Opus 5.5. 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

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

plan-synthesizer

Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …

testdouble/han · 159 tokens

discussion-facilitator

Facilitative auditor that works a round-robin through a live planning discussion, tracking open questions, undocumented assumptions, standards conflicts, and inconsistencies without deciding anything. Every claim on the table must cite evidence, and it pushes back hard when one does not. Use when a planning…

testdouble/han · 160 tokens

system-architect

Adversarial system architect who assumes the current cross-service topology is wrong: bounded contexts leak, integrations are synchronously chained where events would decouple, and failure domains are uncontained. Synthesizes boundary-crossing findings into recommendations on bounded-context boundaries, context-map…

testdouble/han · 188 tokens

software-architect

Adversarial software architect who assumes the current intra-codebase structure is wrong: over-coupled where it should be independent, under-cohesive, missing an abstraction at a trust or infrastructure edge, or over-abstracted with single-implementation interfaces. Synthesizes structural, behavioral, concurrency, and…

testdouble/han · 195 tokens

bounded-context-critic

Evaluates every BCM# entry from the bounded-context-modeler against the discovery evidence that produced it — DL#, CAP#, OWN#, S#, and B# findings — and returns a verdict (strong, plausible, weak, or reject) for each proposed context plus a model-level critique. For each context, surfaces the strongest supporting and…

testdouble/han · 174 tokens