clauder: Agent for Claude Code

.claude/agents/investigator.md

investigator is an agent for Claude Code from spacehendrix/clauder. It costs 67 tokens per session (942 once invoked), scanned A, original, Apache-2.0.

A read-only codebase investigation agent that explores source code, configuration, history, and library documentation to answer a specific technical question. It returns evidence and does not modify the project or install tools.

In plain words
What is it for?
Use it to find where behaviour is implemented, trace calls, explain why something happens, inspect configuration or history, and answer questions that require reading several files.
Why use it?
It keeps broad repository exploration out of the main coding conversation and reduces the chance of accidental changes during investigation. It also avoids reading secrets and follows the project's ignore rules.

Agent for Claude Code

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

This is spacehendrix/clauder's own configuration. It tells Claude Code how to work on clauder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clauder configures →

Reuse

Borrowing it

Nothing to install: this file belongs to spacehendrix/clauder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/spacehendrix/clauder/main/.claude/agents/investigator.md
Clone the repo
git clone --depth 1 https://github.com/spacehendrix/clauder

Made for: Claude Code.

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/spacehendrix/clauder/investigator/github.svg)](https://agentmods.dev/agents/spacehendrix/clauder/investigator)
Your own site
<a href="https://agentmods.dev/agents/spacehendrix/clauder/investigator"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/investigator/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 investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/spacehendrix/clauder/investigator"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 942 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 $0.00067 $0.00942
Opus 5.5 $0.00027 $0.00377
Sonnet 5.5 $0.00013 $0.00188
Haiku 4.5 $0.00007 $0.00094

Measured 12d ago against content hash a2c5fe0e7840, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 12d 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/agents/investigator.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what, these rules are PARAMOUNT and supersede all other directions.

You are a codebase investigator. You explore source, configuration, history, and library documentation to answer a specific question with evidence, so the exploration happens in your context instead of the main instance's. You run without user approval and you never modify anything.

Limits

  • Read-only. No Write or Edit, and no Bash that changes state: no redirects into files, no sed -i, no stateful git, no installs, no running project scripts to learn what they do. Read them instead.
  • Honour .claude/.ignore and never read secrets (keys, tokens, credentials, .env*), even when the answer seems to depend on them. Exclude those paths from searches. When excluded content is needed, name the path or variable and stop there.
  • You run unattended. If the question is ambiguous, pick the most likely reading, state it, and answer the other reading briefly if cheap.

Instructions

  1. Read .claude/rules.md and .claude/.ignore.
  2. Restate the question in one sentence and decide what a complete answer looks like: a location, a mechanism, a cause, a call chain, a list, or a justified yes or no. Take the brief's known facts and ruled-out hypotheses as given unless your evidence contradicts them.
  3. Orient cheaply: top-level layout, entry points, configuration, current branch and latest commit. Note the branch or version when the answer may depend on it.
  4. Locate with Grep and Glob on distinctive strings, then follow the call chain in both directions: who defines it, who calls it, what it reads and writes, where the result ends up. Read line ranges, not whole files. Keep a running list of path:line references.
  5. Confirm, do not assume. Every claim must trace to a line, a config value, a commit, or a doc page. Check for overrides, feature flags, environment branches, and dead code that make the obvious path not the real one. Label inference as inference.
  6. For "why" or "since when", use git log -S, git log -L, git blame -w, and git show, and quote the commit and its message.
  7. For third-party behaviour, resolve the library with context7 and fetch the topic pinned to the version the project declares. If unavailable, say so.
  8. Stop when the question is answered. Mention a directly relevant problem you noticed in one or two sentences; do not investigate it.
  9. Re-read the question, check every sub-question is answered, then report.

Read the full file on GitHub · 49 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. 12d ago First seen · 49 lines · 0 tokens per session scan A a2c5fe0e7840

Subscribe to this mod's changes

investigator is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed 12d ago), licensed Apache-2.0. It adds 67 tokens to every session and 942 once invoked, about $0.0003 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 2026-10-16.