soul-create

soul-create is a skill for Claude Code, Codex from jmagly/aiwg. It costs 34 tokens per session (1,585 once invoked), scanned A, original, MIT.

A generator for a SOUL.md identity file, a document that defines an agent or project's persona, voice, beliefs, and boundaries. It can build the file from writing samples, guided questions, an existing voice profile, or a plain-language description.

In plain words
What is it for?
Use it to create a persona or project identity document from source material or interactive prompts.
Why use it?
It turns scattered examples or ideas about an identity into a consistent file that can be used as a shared reference.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is User: "Build a soul from these blog posts: ./samples/*.md".

Good fit Use it to create a persona or project identity document from source material or interactive prompts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jmagly/aiwg
agentmods
npx agentmods add skills/jmagly/aiwg/soul-create

Made for: Claude Code, Codex.

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-create

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmagly/aiwg/soul-create/github.svg)](https://agentmods.dev/skills/jmagly/aiwg/soul-create)
Your own site
<a href="https://agentmods.dev/skills/jmagly/aiwg/soul-create"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/soul-create/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 soul-create

Your own site · 80×15
<a href="https://agentmods.dev/skills/jmagly/aiwg/soul-create"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/soul-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,585 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 189
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00034 $0.01585
Opus 5 $0.00017 $0.00792
Sonnet 5 $0.00007 $0.00317
Haiku 4.5 $0.00003 $0.00159

Measured 7d ago against content hash 83249d9f3d8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

soul-create 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.

agentic/code/addons/aiwg-utils/skills/soul-create/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

soul-create

Generate a SOUL.md identity file from source material or interactive prompts.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

  • "SOUL.md" / "project identity" → project soul/identity definition
  • "write the soul file" → soul document creation

Behavior

When triggered, this skill generates a SOUL.md file following the community template structure. It can work from:

  1. Source material — writing samples, blog posts, tweets, essays
  2. Interactive prompts — guided questions to define identity
  3. Existing voice profile — bridge from AIWG voice profile to SOUL.md
  4. Natural language description — "a skeptical engineer who values simplicity"

Generation Process

  1. Gather identity signals from input:

    • Worldview patterns (what does this person believe?)
    • Opinion patterns (what specific takes emerge?)
    • Vocabulary fingerprint (signature terms, avoided terms)
    • Rhetorical style (how are arguments structured?)
    • Boundaries (what does this person refuse to do?)
    • Contradictions (where are they inconsistent?)
  2. Map to SOUL.md sections:

    Section Source Signal
    Who I Am Self-description, background, context
    Worldview Recurring beliefs across samples
    Opinions Specific takes organized by domain
    Standards What "done" means for this persona; bar for completion; how complete-vs-fast tension is resolved
    Interests Topics that generate depth/enthusiasm
    Current Focus Active projects, recent themes
    Influences Referenced thinkers, cited works
    Vocabulary Terms with specific personal meanings
    Tensions Contradictory beliefs (a feature, not a bug)
    Boundaries What triggers refusal or pushback
    Pet Peeves What generates strong negative reactions

    The Standards section is a first-class identity dimension alongside worldview, values, and voice. It captures the persona's bar for completion — what "done" looks like and how this persona resolves the complete-vs-fast tension. A pragmatic shipping persona, a craft persona, and a regulated-industry persona all answer this differently, and the answer is load-bearing for behavior. Suggested shape (hybrid prose + optional structured lists):

Read the full file on GitHub · 193 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 · 193 lines · 34 tokens per session scan A 83249d9f3d8b

Subscribe to this mod's changes

soul-create is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 1,585 once invoked, about $0.0002 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 2026-09-05.