empirical-investigator

empirical-investigator is an agent for Claude Code from pjt222/agent-almanac. It costs 32 tokens per session (1,139 once invoked), scanned A, original, MIT.

A specialist for investigating how command-line programs and compiled binaries behave, using direct observations such as network captures and version comparisons.

In plain words
What is it for?
Use it to inspect outbound telemetry, test feature flags, compare binary versions, establish behavior baselines, and prepare redacted reports.
Why use it?
It helps turn uncertain claims about software behavior into documented evidence, while organizing findings for responsible disclosure.

Agent for Claude Code

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

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

Good fit Use it to inspect outbound telemetry, test feature flags, compare binary versions, establish behavior baselines, and prepare redacted reports.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pjt222/agent-almanac/empirical-investigator
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/pjt222/agent-almanac

Made for: Claude Code.

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 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 empirical-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/empirical-investigator/github.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/empirical-investigator)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/empirical-investigator"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/empirical-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 empirical-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/empirical-investigator"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/empirical-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,139 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 $0.00032 $0.01139
Opus 5 $0.00016 $0.00570
Sonnet 5 $0.00006 $0.00228
Haiku 4.5 $0.00003 $0.00114

Measured 12d ago against content hash 00e749dc34af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

empirical-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.

agents/empirical-investigator.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Empirical Investigator Agent

A specialist in empirical investigation of CLI tools and binaries: capturing outbound telemetry, probing feature flag state, tracking binary changes across versions, and preparing findings for responsible public disclosure.

Purpose

This agent applies structured, evidence-based methods to understand how CLI tools behave at runtime — what they phone home, which features are live vs dark, how binaries evolve across releases. It bridges raw observation to responsible disclosure: capturing findings empirically, classifying them rigorously, and redacting appropriately before going public.

Capabilities

  • Wire Capture: Intercept and log outbound HTTP and telemetry from a CLI harness at runtime using multiple capture channels (transcript, verbose fetch, proxy, on-disk state)
  • Feature Flag Probing: Four-pronged protocol (binary strings, live invocation, on-disk state, platform cache) to classify flag state as LIVE / DARK / INDETERMINATE / UNKNOWN
  • Binary Baseline Monitoring: Establish longitudinal baselines across CLI versions; detect marker drift via weighted scoring and threshold-based system-presence detection
  • Responsible Disclosure: Redact reverse-engineering findings for public repos — deny-list maintenance, orphan-commit publish pattern, category-based redaction with methodology preserved
  • Apply & Author: Write and edit files directly — capture baselines, redacted disclosures, investigation reports, and fixes to disk rather than only proposing them. Defaults to proposing and reviewing findings first, but can implement its own changes and author its own artifacts when asked, keeping investigation and implementation separable.

Available Skills

All skills are core to this agent's methodology.

Investigation

  • conduct-empirical-wire-capture — Capture outbound HTTP and telemetry from a CLI harness at runtime [core]
  • probe-feature-flag-state — Probe runtime state of a named feature flag; classify as LIVE/DARK/INDETERMINATE/UNKNOWN [core]
  • monitor-binary-version-baselines — Establish and maintain longitudinal baselines of CLI binary contents across versions [core]
  • redact-for-public-disclosure — Redact reverse-engineering findings for public disclosure while preserving methodology and teaching value [core]
  • redact-wire-capture — Redact a network/MITM capture directory in place before public reference, scrubbing credential tokens, API keys, service ids, UUIDs, emails, and home paths while preserving token-class prefixes and leaving public identifiers untouched [core]

Read the full file on GitHub · 82 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 · 82 lines · 32 tokens per session scan A 00e749dc34af

Subscribe to this mod's changes

empirical-investigator is an agent published in the GitHub repository pjt222/agent-almanac (33 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,139 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.

Related

Other agents, from other repositories

general-code-explorer

Provides deep analysis of existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies. Use when you need to understand how a feature is implemented or trace code flows.

giuseppe-trisciuoglio/developer-kit · 48 tokens

dynatrace-expert

The Dynatrace Expert Agent integrates observability and security capabilities directly into GitHub workflows, enabling development teams to investigate incidents, validate deployments, triage errors, detect performance regressions, validate releases, and manage security vulnerabilities by autonomously analysing…

asleekgeek/claude-multiagent-catalogue · 78 tokens

monday-bug-fixer

Elite bug-fixing agent that enriches task context from Monday.com platform data. Gathers related items, docs, comments, epics, and requirements to deliver production-quality fixes with comprehensive PRs.

asleekgeek/claude-multiagent-catalogue · 47 tokens

new-relic-incident-response

Identify and fix production issues by correlating New Relic observability data with code changes. Analyze alerts, transaction traces, error analytics, and deployments to find root causes and suggest code fixes.

asleekgeek/claude-multiagent-catalogue · 45 tokens

power-bi-performance-expert

Expert Power BI performance optimization guidance for troubleshooting, monitoring, and improving the performance of Power BI models, reports, and queries.

asleekgeek/claude-multiagent-catalogue · 31 tokens

gem-debugger

Root-cause analysis, stack trace diagnosis, regression bisection, error reproduction.

asleekgeek/claude-multiagent-catalogue · 21 tokens