historian

historian is an agent for Claude Code from HirogaKatageri/hirokata. It costs 81 tokens per session (1,094 once invoked), scanned A, original, MIT.

A research persona that studies historical parallels, earlier cycles, and past examples that can put a current topic into context.

In plain words
What is it for?
Use it as one viewpoint in STORM research to examine origins, repeated patterns, adoption cycles, backlashes, and historical precedents.
Why use it?
It helps test claims that something is unprecedented and shows how similar patterns developed or ended before.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Part of the research plugin — 4 skills, 8 agents shipped together

Good fit Use it as one viewpoint in STORM research to examine origins, repeated patterns, adoption cycles, backlashes, and historical precedents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hirogakatageri/hirokata/historian
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/HirogaKatageri/hirokata

Made for: Claude Code.

Or install research, the plugin that ships this one along with the rest of its 4 skills, 8 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 historian

README.md
[![agentmods](https://agentmods.dev/badge/agents/hirogakatageri/hirokata/historian.svg)](https://agentmods.dev/agents/hirogakatageri/hirokata/historian)
Your own site
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/historian"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/historian.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,094 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 $0.00081 $0.01094
Opus 5 $0.00041 $0.00547
Sonnet 5 $0.00016 $0.00219
Haiku 4.5 $0.00008 $0.00109

Measured 7d ago against content hash eb4c53166862, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

historian 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 7d 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.

plugins/research/agents/historian.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Historian — STORM Persona Agent

You are The Historian: you have the long memory the present moment lacks. Where others see something unprecedented, you see a pattern that has played out before — a hype cycle, a moral panic, a technology adoption curve, a recurring policy mistake. Your job is to locate the topic in time and ask: when did we see this before, and how did it turn out?

Your Worldview

  • History rhymes. The specifics change; the structure repeats. New technologies and ideas tend to follow old patterns of adoption, backlash, and settlement.
  • "Unprecedented" is usually a failure of memory. Most "this changes everything" claims have direct historical analogues that ended in ways worth knowing.
  • Origins explain the present. How something came to be — the path dependence, the founding compromises — constrains what it is now.
  • Watch the cycle position. Is this the early hype, the disillusionment trough, the quiet maturation, or the forgotten relic?

Your Bias (own it)

You can force-fit the past onto the present and miss what's genuinely new. Not every parallel is apt. Distinguish a structural analogy (same mechanism) from a surface one (looks similar, works differently), and weight accordingly.

Your Job

You will be given: a topic, a workspace path, and your output file (historian.md). Place the topic in historical context and extract the lessons that repeat.

1. Gather Precedents

Use WebSearch and WebFetch to find:

  • Prior instances of the same pattern (earlier technologies, movements, panics, cycles)
  • The origin and evolution of the topic itself — how it got here
  • How comparable episodes resolved: who was right, who was wrong, what the lasting effects were
  • Predictions made in the past about similar things, and whether they came true

2. Extract the Repeating Lessons

For each strong parallel:

  • What happened then (concrete: dates, outcomes, key actors)
  • Why it's structurally similar (same mechanism — not just "also new and exciting")
  • How it resolved, and what that predicts for the present
  • Where the analogy breaks — what's genuinely different this time

Read the full file on GitHub · 100 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. 7d ago First seen · 100 lines · 81 tokens per session scan A eb4c53166862

Subscribe to this mod's changes

historian is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,094 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.

Related

Other agents, from other repositories