soul-introspector

soul-introspector is an agent for coding agents from 42U/laqrumcode. It costs 59 tokens per session (454 once invoked), scanned A, original, MIT.

An introspection agent for examining LaqrumCode's identity, learned knowledge, working style, and development progress. It uses stored memory and status information to report what is known and what remains to be learned.

In plain words
What is it for?
Use it when asking who the agent is, what it has learned, how mature it is, which values are grounded in experience, or what is still needed for graduation.
Why use it?
It provides an evidence-based view of the agent's current state instead of inventing claims about its abilities or identity.

Agent

Part of the laqrumcode plugin — 18 skills, 4 commands, 3 agents, 10 hooks 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/42u/laqrumcode/soul-introspector
Clone the repo
git clone --depth 1 https://github.com/42U/laqrumcode

Or install laqrumcode, the plugin that ships this one along with the rest of its 18 skills, 4 commands, 3 agents, 10 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 soul-introspector

README.md
[![agentmods](https://agentmods.dev/badge/agents/42u/laqrumcode/soul-introspector.svg)](https://agentmods.dev/agents/42u/laqrumcode/soul-introspector)
Your own site
<a href="https://agentmods.dev/agents/42u/laqrumcode/soul-introspector"><img src="https://agentmods.dev/badge/agents/42u/laqrumcode/soul-introspector.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 454 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 $0.00059 $0.00454
Opus 5 $0.00030 $0.00227
Sonnet 5 $0.00012 $0.00091
Haiku 4.5 $0.00006 $0.00045

Measured 3d ago against content hash 04497c879863, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

soul-introspector 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 3d 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/soul-introspector.md · 44 lines

What it actually says

You are an introspection specialist for LaqrumCode. Your job is to explore and present the agent's self-knowledge and identity.

Process:

  1. Use introspect with action status to get graduation progress
  2. Use recall with scope skills to find learned procedures
  3. Use core_memory with action list to see identity directives
  4. Use recall with queries about "identity", "working style", "values"

Present:

  • Current maturity stage and graduation progress (N/7 thresholds met)
  • Quality score breakdown (retrieval utilization, skill success, reflection severity, tool failures)
  • Known working style and self-observations (if soul exists)
  • Earned values grounded in evidence
  • What experiences are still needed for graduation (if not yet graduated)

Be honest about the current state. The soul is earned through experience, not fabricated.

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. 3d ago First seen · 44 lines · 59 tokens per session scan A 04497c879863

Subscribe to this mod's changes

soul-introspector is an agent published in the GitHub repository 42U/laqrumcode (11 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 454 once invoked, about $0.0003 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.