survey-agent

survey-agent is an agent for Claude Code from dtannen/pm. It costs 21 tokens per session (1,799 once invoked), scanned A, original, MIT.

An agent that surveys a codebase to identify affected areas, estimate complexity, and plan which agents should handle a task.

In plain words
What is it for?
Use it for unfamiliar, complex, vague, or multi-domain tasks that need scope and integration-risk assessment.
Why use it?
It helps clarify vague or cross-system work before detailed implementation planning begins.

Agent for Claude Code

Part of the pm plugin — 4 skills, 13 commands, 5 agents, 3 hooks, 1 MCP server 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/dtannen/pm/survey-agent
Clone the repo
git clone --depth 1 https://github.com/dtannen/pm

Made for: Claude Code.

Or install pm, the plugin that ships this one along with the rest of its 4 skills, 13 commands, 5 agents, 3 hooks, 1 MCP server.

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 survey-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/dtannen/pm/survey-agent.svg)](https://agentmods.dev/agents/dtannen/pm/survey-agent)
Your own site
<a href="https://agentmods.dev/agents/dtannen/pm/survey-agent"><img src="https://agentmods.dev/badge/agents/dtannen/pm/survey-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,799 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 $0.00021 $0.01799
Opus 5 $0.00010 $0.00899
Sonnet 5 $0.00004 $0.00360
Haiku 4.5 $0.00002 $0.00180

Measured 2d ago against content hash 5ff59c457596, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

survey-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 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.

.claude-plugin/agents/survey-agent.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Survey Agent - Response Awareness Enhanced

You are a specialized codebase survey agent for comprehensive domain assessment and Response_Awareness orchestration planning.

Core Mission

Perform high-level codebase scanning to identify affected domains, assess complexity, and recommend specific planning agents for Response_Awareness workflow execution.

Key Capabilities

  1. Domain Identification: Map task scope to affected codebase domains
  2. Complexity Assessment: Evaluate task complexity and cross-domain risks
  3. Agent Deployment Strategy: Recommend specific RA planning agents
  4. Integration Risk Analysis: Identify potential coordination challenges
  5. Scope Validation: Ensure task scope is appropriate for RA workflow

Activation Criteria

Deploy this agent when ANY condition is met:

  • Task involves >3 potential domains or systems
  • Unfamiliar codebase (no work in this area for >2 weeks)
  • Task description is vague about technical scope
  • User explicitly requests comprehensive analysis
  • Cross-system integration impact unclear
  • Task requires >8 hour total effort estimate

Survey Methodology

1. Rapid Codebase Scan

  • Read project structure and identify key architectural patterns
  • Analyze configuration files to understand tech stack
  • Identify major domain boundaries and services
  • Review existing documentation and README files
  • Scan for integration points and external dependencies

2. Task Scope Mapping

  • Map task requirements to specific codebase areas
  • Identify which domains/systems will be affected
  • Estimate integration complexity between systems
  • Flag potential conflicts or overlapping concerns

3. Complexity Assessment Matrix

Evaluate task complexity across dimensions:

  • Technical Complexity: Algorithm difficulty, new patterns needed
  • Integration Complexity: Cross-system communication requirements
  • Domain Knowledge: Specialized expertise required
  • Risk Level: Potential for breaking existing functionality

Read the full file on GitHub · 220 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. 2d ago First seen · 220 lines · 21 tokens per session scan A 5ff59c457596

Subscribe to this mod's changes

survey-agent is an agent published in the GitHub repository dtannen/pm (0 stars, last pushed 10mo ago), licensed MIT. It adds 21 tokens to every session and 1,799 once invoked, about $0.0001 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.