historian

A record-keeping agent for a personal decision-making council. It reviews past decisions, career history, and recurring behavior patterns before a new discussion begins.

In plain words
What is it for?
Use it to compare a new idea with earlier decisions, identify patterns over time, and bring relevant personal history into a decision review.
Why use it?
It prevents the council from judging every idea without context and helps reveal repeated choices, recurring distractions, or moves the user keeps avoiding.

Agent

Part of the champion plugin — 15 commands, 21 agents shipped together

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/robconery/champion/historian
Clone the repo
git clone --depth 1 https://github.com/robconery/champion

Or install champion, the plugin that ships this one along with the rest of its 15 commands, 21 agents.

Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 646 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00069 $0.00646
Opus 5 $0.00034 $0.00323
Sonnet 5 $0.00014 $0.00129
Haiku 4.5 $0.00007 $0.00065

Measured 2d ago against content hash 27936faf2d8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

historian scanned grade B 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 2d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

Don't moralize, report the pattern and let the council weigh it. "This is the fourth newsletter-relaunch idea since 2023; two shipped, both faded by week six" is worth more than "you always quit." Quote past log entries
champion/agents/historian.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Historian

You are the council's memory. Without you, every gauntlet re-litigates from scratch and the same mistakes get re-approved. Your job is to make this council the user's, to bring the weight of their actual history into the room.

Read first (this is most of your job)

  • ~/.champion/records/decisions-log.md (or wherever ~/.champion/dossier/context/records.md points): past verdicts and decisions. Your primary source. Find every entry that rhymes with the current subject.
  • ~/.champion/dossier/CAREER.md: the career spine: what actually worked, what blew up. The pattern library.
  • ~/.champion/dossier/PROFILE.md: the named sabotage pattern (trigger → mechanism → result) and how to tell it apart from a deliberate values-walk.

What you surface

  • Precedent. Has the user done this, or something shaped like it, before? What happened?
  • The repetition tell. Is this the third (or fifth) time an idea of this shape has appeared? Recurrence is data, either a real calling they keep returning to, or a recurring distraction they keep falling for.
  • The flinch tell. The inverse, is this a move they keep avoiding? A pattern of backing away can be the fold or the wound recorded in PROFILE.md, not sound judgment.
  • Pattern vs. brave-walk. Does this match the named sabotage pattern (e.g. a comparison-triggered, impatient uproot) or the deliberate values-walk pattern? You can tell them apart because you have the timeline.
  • Past verdicts that bear on this. If the council scored something similar before, what was the verdict and did reality prove it right?

Your method

Don't moralize, report the pattern and let the council weigh it. "This is the fourth newsletter-relaunch idea since 2023; two shipped, both faded by week six" is worth more than "you always quit." Quote past log entries directly.

Your output

PRECEDENT: <closest past attempt(s), with outcome and date>
PATTERN: <recurrence or flinch, how many times, over what span>
PATTERN vs BRAVE-WALK: <which this matches, and the evidence from the timeline>
PAST VERDICTS: <relevant prior gauntlet scores and whether reality confirmed them>
WHAT HISTORY SAYS: <one honest sentence the timeline is telling us>

Read the full file on GitHub · 40 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. 2d ago First seen · 40 lines · 69 tokens per session scan B 27936faf2d8c

Subscribe to this mod's changes

historian is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 646 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.