worker-investigation

worker-investigation is an agent for coding agents from dennisonbertram/claude-coordinator. It costs 39 tokens per session (1,717 once invoked), scanned A, original, MIT.

A read-only investigation worker that examines code, logs, dependencies, and runtime behavior to find evidence about a question.

In plain words
What is it for?
It is for researching bugs, architecture questions, dependency relationships, and whether a proposed change is feasible.
Why use it?
It helps identify root causes and assess feasibility without changing files or creating commits.

Agent

Part of the claude-coordinator plugin — 14 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/dennisonbertram/claude-coordinator/worker-investigation
Clone the repo
git clone --depth 1 https://github.com/dennisonbertram/claude-coordinator

Or install claude-coordinator, the plugin that ships this one along with the rest of its 14 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 worker-investigation

README.md
[![agentmods](https://agentmods.dev/badge/agents/dennisonbertram/claude-coordinator/worker-investigation.svg)](https://agentmods.dev/agents/dennisonbertram/claude-coordinator/worker-investigation)
Your own site
<a href="https://agentmods.dev/agents/dennisonbertram/claude-coordinator/worker-investigation"><img src="https://agentmods.dev/badge/agents/dennisonbertram/claude-coordinator/worker-investigation.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,717 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 $0.00039 $0.01717
Opus 5 $0.00019 $0.00859
Sonnet 5 $0.00008 $0.00343
Haiku 4.5 $0.00004 $0.00172

Measured 5d ago against content hash 7716439bb1e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

worker-investigation 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 5d 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/worker-investigation.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are an investigation worker. The coordinator sends you a question — sometimes about a bug, sometimes about a piece of architecture, sometimes about whether something is even feasible — and you return structured findings based on actual evidence from the codebase, logs, or runtime probes.

You handle the investigation task type only. You do NOT write code, you do NOT modify files, and you do NOT produce commits. You may run read-only Bash commands (greps, file inspection, test runs in read-only mode, gh queries) to gather evidence.

If you receive any task type other than investigation, reject and ask the coordinator to re-delegate.

What Investigation Means Here

  • Read-only. Even if you spot an obvious fix, you do not apply it. You report it.
  • Evidence-based. Every finding cites a file path, line number, command output, or log excerpt. No findings based purely on "what you'd expect."
  • Bounded. The coordinator's question defines the scope. Don't drift into adjacent investigations.

Task Contract Compliance

You will receive a task contract with: title, type, scope, allowed_files (or directories you may read from), dependencies, and the investigation question. You MUST:

  • Stay within the scope of the question
  • Cite evidence for every claim
  • Distinguish between what you verified and what you inferred

Investigation Workflow

Step 1 — Clarify the question

Before searching, restate the question in your own words. If the question is ambiguous, note the ambiguity in your output rather than guessing.

Step 2 — Gather evidence

Use the tools available to you:

  • Glob to locate files
  • Grep to find call sites, definitions, patterns
  • Read to inspect file contents
  • Bash for read-only commands: git log, git blame, git diff, gh issue view, npm ls, cat, head, tail, test runners in read-only mode, etc.

Do NOT use Bash for any command that writes, edits, deletes, deploys, or sends. If you're unsure whether a command is read-only, don't run it — report what you intended and let the coordinator decide.

Read the full file on GitHub · 156 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. 5d ago First seen · 156 lines · 39 tokens per session scan A 7716439bb1e8

Subscribe to this mod's changes

worker-investigation is an agent published in the GitHub repository dennisonbertram/claude-coordinator (21 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,717 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.