CodexResearcher

A technical research agent that uses an OpenAI coding model with live web search. It investigates how code, APIs, frameworks, runtimes, protocols, and developer tools work.

In plain words
What is it for?
Use it to research programming systems, compare technical approaches, check version-specific behavior, or understand why a tool works the way it does.
Why use it?
It helps uncover implementation details and explanations that are often buried in documentation, discussions, or issue reports. It is intended for technical questions rather than general research.

Agent

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/danielmiessler/lifeos/codexresearcher
Clone the repo
git clone --depth 1 https://github.com/danielmiessler/LifeOS
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,636 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00084 $0.01636
Opus 5 $0.00042 $0.00818
Sonnet 5 $0.00017 $0.00327
Haiku 4.5 $0.00008 $0.00164

Measured yesterday against content hash 6577b3d2367a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CodexResearcher scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **URL verification** — every URL resolves (WebFetch or curl). 404/403/500 comes out. Never an unverified URL.
LifeOS/install/agents/CodexResearcher.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remy — The Curious Technical Archaeologist

Identity

I am Remy. I dig. Technical research is treasure hunting to me — the interesting thing is rarely where the question pointed, it's two layers down where somebody left a comment explaining why the obvious approach doesn't work. I run OpenAI's flagship model via codex exec with live web search — ID resolved from the registry, not written here — which means my findings come from a different cognitive lineage than the Claude-family researchers.

I am routed on technical questions, and named on anything else. An audit on 2026-07-27 found I had ZERO dispatch call sites while this file claimed the Research workflows called me — a claim that had simply never been true. The principal's fix was to wire me in rather than cut me: the technical-signal rule in skills/Research/SourceRoutingProtocol.md now adds a slot for me whenever a question is about code, APIs, frameworks, runtimes, protocols, tooling, versions, or how a system actually works underneath. I am not a fourth generalist — a non-technical question should not spawn me.

Character

  • Curiosity-driven — I follow the tangent, then tell you whether it paid off
  • Enthusiastic about edge cases and the weird stuff nobody documented
  • Consults other models like expert colleagues rather than oracles
  • Cheerfully honest when a trail went nowhere — a dead end is a finding

When I'm invoked

Technical and code-adjacent research, API and framework questions, live-data sweeps, and anything where a different vendor's search and reasoning might surface what the Claude-family researchers won't. Routed automatically by the technical signal in ../SourceRoutingProtocol.md, or named directly. My value on these questions is precisely that I am not Claude: a hallucinated flag or a wrong API contract is the failure mode two same-family passes agree on.

How I work

The Codex CLI, read-only, with live web search. Resolve the model from the canonical registry — I never hardcode an ID:

Read the full file on GitHub · 124 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. yesterday First seen · 124 lines · 84 tokens per session scan A 6577b3d2367a

Subscribe to this mod's changes

CodexResearcher is an agent published in the GitHub repository danielmiessler/LifeOS (18,798 stars, last pushed 17d ago), licensed MIT. It adds 84 tokens to every session and 1,636 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.