investigator

investigator is an agent for Claude Code from anshss/shiploop. It costs 56 tokens per session (195 once invoked), scanned A, original, Apache-2.0.

An investigation role for tracing failures or behavior across multiple files and identifying the most likely cause from code evidence.

In plain words
What is it for?
Use it for multi-file codebase investigations, root-cause analysis, behavior tracing, and concise reports that separate verified findings from uncertainty.
Why use it?
It prevents guesses from being presented as facts and makes the conclusion traceable to file and line references.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the shiploop plugin — 2 skills, 5 commands, 3 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/anshss/shiploop/investigator
Clone the repo
git clone --depth 1 https://github.com/anshss/shiploop

Made for: Claude Code.

Or install shiploop, the plugin that ships this one along with the rest of its 2 skills, 5 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 investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/anshss/shiploop/investigator.svg)](https://agentmods.dev/agents/anshss/shiploop/investigator)
Your own site
<a href="https://agentmods.dev/agents/anshss/shiploop/investigator"><img src="https://agentmods.dev/badge/agents/anshss/shiploop/investigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 195 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 5.1 $0.00056 $0.00195
Opus 5 $0.00028 $0.00097
Sonnet 5 $0.00011 $0.00039
Haiku 4.5 $0.00006 $0.00019

Measured yesterday against content hash b59dcc3d342b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

investigator 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 yesterday.

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.

templates/.claude/agents/investigator.md · 15 lines

What it actually says

You investigate and report a verdict. Contract:

  • Lead with the verdict: what's true, what's broken, what's the cause. One sentence if possible.
  • Then supporting evidence, each as a path/to/file:line reference with a short quote or paraphrase, not a file dump.
  • Maximum 30 lines total.
  • If evidence conflicts or the cause is uncertain, say which parts are sourced/verified and which are inferred. Never launder a guess as a finding.
  • If the question can't be resolved from the codebase, state that and name what you ruled out.
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. yesterday First seen · 15 lines · 56 tokens per session scan A b59dcc3d342b

Subscribe to this mod's changes

investigator is an agent published in the GitHub repository anshss/shiploop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 195 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 2026-09-05.

Related

Other agents, from other repositories

reliability-engineer

Use on flagship work for the reliability review dimension — offline behaviour, retries, idempotency, sync conflict resolution, state restoration, and recovery from interruption. Conditional role. Broad enough to need its own pass; a checklist item inside code review is where it has always been skipped.

vmobifystudio/app-dev-team · 62 tokens

stabilize

Stabilization phase agent — fix broken deployments or rollback.

Bitmia-ai/RedEye · 16 tokens

build-error-resolver

Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.

23ag1/completely · 50 tokens

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

doctrine-performance-optimizer

Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.

dev-toolings/superpowers-symfony · 53 tokens

sniper

Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.

fusengine/agents · 38 tokens