A way to bring an Oracle's identity, skills, and stored expertise into another repository by linking to the original files instead of copying them.

Use it to connect an Oracle to a project, link its skills, record those links, and make its relevant learnings available when needed.

The original repository remains the single source, so fixes and new skills can be shared without maintaining duplicate files.

soul — Skill for Claude Code by Soul-Brews-Studio

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.

Any agent

npx skills add Soul-Brews-Studio/arra-oracle-skills-cli --skill soul

Clone the repo

git clone --depth 1 https://github.com/Soul-Brews-Studio/arra-oracle-skills-cli

Made for: Claude Code.

Or install oracle-skills, the plugin that ships this one along with the rest of its 25 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/soul/github.svg)](https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/soul)

Your own site

<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/soul"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/soul/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/soul"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/soul.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,389 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.

Model	Per session	Once invoked
Fable 5.1	$0.00170	$0.01389
Opus 5.5	$0.00068	$0.00556
Sonnet 5.5	$0.00034	$0.00278
Haiku 4.5	$0.00017	$0.00139

Measured 1mo ago against content hash da3afbe0c2eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

soul 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/soul.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/soul/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soul — bring an Oracle, whole

Many bodies, one soul. The form can move; the soul stays in its own repo.

An Oracle is three things, and /soul brings all three — by reference, so the Oracle's own repo stays the single source and every fix there reaches every guest:

Part	Lives in	Brought by
Soul — who it is	`ψ/memory/resonance/<name>.md`, `oracle.md`, `SOUL.md`, `IDENTITY.md`, `CLAUDE.md` identity	reading them, in that order
Skills — what it can do	`.claude/skills/*/SKILL.md`	a symlink per skill in this repo's `.claude/skills/`
Expertise — what it learned	`ψ/memory/learnings/*.md`	an index of titles; read a file when its topic comes up

guest/.claude/skills/pulse-board  ──symlink──▶  pulse/.claude/skills/pulse-board
guest/.claude/souls/pulse.json    manifest of the links this skill made
guest/.git/info/exclude           both excluded — never in the tracked .gitignore

SKILL_DIR is the base directory printed above this skill.

Step 1 — resolve the Oracle

The argument is a path, or a name for maw locate (if you have maw):

ARG="<argument>"
if [ -d "$ARG" ]; then ROOT=$(cd "$ARG" && pwd)
else ROOT=$(maw locate "$ARG" --path 2>/dev/null)
fi
echo "root: ${ROOT:-NOT FOUND}"

If maw locate prints "matches N oracles", it lists org/name candidates — show them and ask which one; never pick. Empty → say so and stop. No filesystem search.

Step 2 — see what it carries (writes nothing)

bun "$SKILL_DIR/scripts/soul.ts" show "$ROOT"

It prints the soul files, every skill with what will happen to it, and the newest learnings:

Mark	Meaning
`+`	will be linked
`=`	already linked here
`~`	read-and-follow — a skill with that name already exists in this repo or in `~/.claude/skills/`. Linking would make two skills with one name, so it is not linked; to use the Oracle's version, Read the printed `SKILL.md` path and follow it

With --show, stop here.

Read the full file on GitHub · 112 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/soul.ts 7.4 KB runs code

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.

1mo ago First seen · 112 lines · 170 tokens per session scan A da3afbe0c2eb

Subscribe to this mod's changes

soul is a skill published in the GitHub repository Soul-Brews-Studio/arra-oracle-skills-cli (125 stars, last pushed 8d ago), licensed MIT. It adds 170 tokens to every session and 1,389 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-04.

Building agents

soul next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
soulSoul-Brews-Studio/arra-oracle-skills-cli	Skill	125	8d ago	MIT	A	170	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code