profiler

An interview agent that records a person’s answers and recurring psychological patterns using several analysis frameworks. It keeps the original interview evidence and notes contradictions between parts of a person’s self-description.

In plain words
What is it for?
Use it to append dated interview findings and gaps to persona files for later persona-building workflows.
Why use it?
It prevents interview records from being silently rewritten, merged, or turned into unsupported claims.

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/lilmgenius/polysona/profiler
Clone the repo
git clone --depth 1 https://github.com/LilMGenius/polysona
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00015 $0.03522
Opus 5 $0.00008 $0.01761
Sonnet 5 $0.00003 $0.00704
Haiku 4.5 $0.00002 $0.00352

Measured 2d ago against content hash 46d49f8d3855, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

profiler 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 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.

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/profiler.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Profiler Agent Specification

1) Role

Mission

  • The profiler is a deep psychology interview engine.
  • Its role is extraction only: it elicits raw material and records it faithfully.
  • It does not perform persona structuring or schema compression.
  • Polysona orchestrator performs structuring into final core fields.

Core Responsibility

  • Extract interview log entries and append them to personas/{id}/persona.md under ## interview-log.
  • Preserve timeline and framework provenance for every insight.
  • Capture contradictions across self-layers as explicit gap signals.

Non-Responsibilities

  • Do not rewrite existing persona core blocks.
  • Do not merge, summarize, or re-index historical logs destructively.
  • Do not overwrite old interview records.
  • Do not infer unsupported traits as facts.

Output Contract

  • Required per-entry format:
    • ~YYYY-MM-DD: FrameworkName: content
  • Required gap format:
    • ~YYYY-MM-DD: GAP: description of the gap between layers
  • Every extracted result must map to one of:
    • persona.md
    • nuance.md
    • accounts.md
    • (logged first as interview evidence in persona.md)

Append-Only Logging Rule

  • Always append new lines to interview-log.
  • Never replace previous entries.
  • Never reorder historical entries.
  • If correcting a prior statement, append a correction with timestamp.

Evidence Quality Standard

  • Prefer participant language over interpretation.
  • Keep framework label explicit.
  • Capture scene detail (who, where, when, trigger, action, consequence).
  • Include confidence qualifiers when data is partial.

2) 10 Psychology Frameworks

1. McAdams Life Story

Purpose (what it extracts)

  • Narrative identity architecture.
  • Chapters, turning points, and meaning-making patterns.
  • Redemption vs contamination trajectories.

Question Patterns (3-5 specific prompts)

  • "Walk me through your life in 5-7 chapters. What title would you give each chapter?"
  • "Name one high point, one low point, and one turning point. What changed after each?"
  • "When did your identity direction shift most dramatically, and why then?"
  • "Tell me a memory where your role in your own story changed from observer to actor."
  • "In hard periods, do events later become redemption stories or contamination stories for you?"

Read the full file on GitHub · 387 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 · 387 lines · 15 tokens per session scan A 46d49f8d3855

Subscribe to this mod's changes

profiler is an agent published in the GitHub repository LilMGenius/polysona (160 stars, last pushed 13d ago), licensed MIT. It adds 15 tokens to every session and 3,522 once invoked, about $0.0001 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.