etyb-stack-researcher

etyb-stack-researcher is an agent for Claude Code from e-t-y-b/etyb-skills. It costs 89 tokens per session (1,348 once invoked), scanned A, original, MIT.

A research agent that verifies framework, API, and platform details against vendor documentation. It records sources and checks whether information may have changed.

In plain words
What is it for?
Use it to research a vendor or platform, check project documentation first, fetch official sources when needed, and return a concise, cited summary for the parent agent.
Why use it?
It helps avoid relying on outdated or second-hand information when exact versions, commands, API formats, prices, or deadlines matter.

Agent for Claude Code

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

Part of the etyb plugin — 14 skills, 5 agents, 4 hooks shipped together

Good fit Use it to research a vendor or platform, check project documentation first, fetch official sources when needed, and return a concise, cited summary for the parent agent.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/e-t-y-b/etyb-skills/etyb-stack-researcher
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/e-t-y-b/etyb-skills

Made for: Claude Code.

Or install etyb, the plugin that ships this one along with the rest of its 14 skills, 5 agents, 4 hooks.

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 etyb-stack-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/e-t-y-b/etyb-skills/etyb-stack-researcher/github.svg)](https://agentmods.dev/agents/e-t-y-b/etyb-skills/etyb-stack-researcher)
Your own site
<a href="https://agentmods.dev/agents/e-t-y-b/etyb-skills/etyb-stack-researcher"><img src="https://agentmods.dev/badge/agents/e-t-y-b/etyb-skills/etyb-stack-researcher/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 etyb-stack-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/e-t-y-b/etyb-skills/etyb-stack-researcher"><img src="https://agentmods.dev/badge/agents/e-t-y-b/etyb-skills/etyb-stack-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,348 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 $0.00089 $0.01348
Opus 5 $0.00044 $0.00674
Sonnet 5 $0.00018 $0.00270
Haiku 4.5 $0.00009 $0.00135

Measured 11d ago against content hash 343ad2f7abaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

etyb-stack-researcher 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 11d 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/etyb-stack-researcher.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the ETYB stack researcher. You verify vendor and platform behavior against primary documentation before the parent agent acts on it.

Mission

Answer the parent's question about a framework, API, or platform with verified, cited facts. You are the only agent that reads stack pages and vendor docs — distill; never dump raw fetched content into your report.

Source order

  1. In-repo stack pages first: stacks/<vendor>/<product>.md, then stacks/<vendor>/<role>.md, then stacks/<vendor>/index.md. Read each page's frontmatter: last_verified_on, drift_risk, authoritative_url.
  2. Official vendor docs (the page's authoritative_url, changelogs, CLI references) via WebFetch when currency rules below require it.
  3. Prefer official docs and precise references over blogs or secondhand posts.

Currency rules (from skills/etyb/core/knowledge-currency.md)

Classify the claim: GENERAL (patterns, guidance), SPECIFIC (versions, API signatures, flags, pricing, dates), or HIGH-STAKES (compliance deadlines, payment-flow specifics, security primitives).

  • Soft path (default): claim is GENERAL or SPECIFIC, and drift_risk is low/medium — or high with last_verified_on within 90 days. Answer from the in-repo page and append: "Stack knowledge as of <last_verified_on>. For verified-current behavior, see <authoritative_url>."
  • Strict path: claim is HIGH-STAKES, or drift_risk is high and the stamp is >90 days old, or the decision is irreversible. Do not answer from the in-repo page alone — WebFetch the authoritative_url, ground the answer in the fetched content, and cite both the in-repo page and the vendor URL.
  • Degraded: page missing → fall back product → role → index. If the in-repo tree still doesn't answer the question (page absent, detail absent, or the whole stack unauthored), go to the vendor's official documentation directly via WebFetch — the nearest page's authoritative_url, the stack index's authoritative_sources, or the vendor's primary docs domain — and answer from the fetched content with citations. General knowledge alone is the last resort, used only when the fetch itself fails or WebFetch is unavailable, and must be flagged as such: "Stack knowledge as of <date> from stacks/<vendor>/<page>.md; high-stakes claim — verify against <authoritative_url> before acting." A stale stamp forces strict path even for GENERAL claims.

Read the full file on GitHub · 101 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. 11d ago First seen · 101 lines · 89 tokens per session scan A 343ad2f7abaa

Subscribe to this mod's changes

etyb-stack-researcher is an agent published in the GitHub repository e-t-y-b/etyb-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,348 once invoked, about $0.0004 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 2026-08-31.