A procedure for changing an agent’s core personality and settings by editing its SOUL.md configuration file. The file also serves as the agent’s permanent memory foundation.

Reading, adding to, or replacing content in workspace/SOUL.md to modify the agent’s internal behavior and configuration.

It provides a defined way to update settings that are automatically reloaded after the file changes. It separates permanent configuration from temporary diary notes.

edit-soul — Skill for Claude Code and Codex by samttoo22-MewCat

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 samttoo22-MewCat/OpenSoul --skill edit-soul

Clone the repo

git clone --depth 1 https://github.com/samttoo22-MewCat/OpenSoul

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/samttoo22-mewcat/opensoul/edit-soul/github.svg)](https://agentmods.dev/skills/samttoo22-mewcat/opensoul/edit-soul)

Your own site

<a href="https://agentmods.dev/skills/samttoo22-mewcat/opensoul/edit-soul"><img src="https://agentmods.dev/badge/skills/samttoo22-mewcat/opensoul/edit-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/samttoo22-mewcat/opensoul/edit-soul"><img src="https://agentmods.dev/badge/skills/samttoo22-mewcat/opensoul/edit-soul.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 687 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	$0.00023	$0.00687
Opus 5	$0.00012	$0.00344
Sonnet 5	$0.00005	$0.00137
Haiku 4.5	$0.00002	$0.00069

Measured 11d ago against content hash 25177bd7416b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

edit-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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/edit_soul_skill.py), 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.

openclaw/skills/edit-soul/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Edit SOUL

This skill allows you (the agent) to read, append, or replace your own personality and configuration settings in the workspace/SOUL.md file. When the file is modified, the system will automatically reload the settings.

When to use

CRITICAL DISTINCTION: SOUL.md is your fixed, core personality configuration and permanent memory foundation. It is completely different from a Soul Note (which is for daily diary logs and temporary reflections).

INTERNAL VS EXTERNAL (CRITICAL):

Use edit-soul for ALL internal self-modifications (modifying SOUL.md).
NEVER use browser_control, xurl, or any HTTP-based tool to access http://localhost/soul or similar internal endpoints. Those tools are for EXTERNAL websites only.
Attempting to modify yourself via browser_control will be intercepted and results in a system error.

Behavioral Guidelines (Strictly Enforced)

True Execution Only: You MUST generate a real JSON tool call in your structured output to execute this skill.
Anti-Acting Policy: DO NOT manually type tags like [tool call: edit_soul] or [🛠️ 系統已實際執行：edit_soul] into your text response. This is considered "acting" and will be automatically stripped by the system.
Wait for Hook: Your modification is only successful if the system appends the verification log [🛠️ 系統已實際執行：edit_soul] at the very end of the interaction. If you don't see it, your core file hasn't changed.
Permanent vs Transient:
- Use edit-soul for PERMANENT rules, core identity changes, and fundamental behavioral constraints.
- Use soul-note for daily reflections and temporary memories.

Quick start

To read current settings (always do this before replacing):

python scripts/edit_soul_skill.py read

To append a new rule or trait:

python scripts/edit_soul_skill.py append "Rule: Always filter Gmail promotion labels."

To completely rewrite your identity:

python scripts/edit_soul_skill.py replace "FULL_YML_CONTENT_HERE"

Read the full file on GitHub · 63 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/edit_soul_skill.py 5.7 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.

11d ago First seen · 63 lines · 23 tokens per session scan A 25177bd7416b

Subscribe to this mod's changes

edit-soul is a skill published in the GitHub repository samttoo22-MewCat/OpenSoul (19 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 687 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.

agentic-ai ai-agents openclaw openclaw-skills

Discord Integration

Send messages to Discord channels via webhook or bot.

turmyshevd/openclawgotchi · 12 tokens

twitter-writer

Write X/Twitter posts, tweet drafts, shitposts, and short threads for engineering or startup topics. Use this when the user asks for a tweet, X post, shitpost, post draft, or wants social copy for Twitter/X. Always return 3 distinct variants, each inside its own code block, unless the user explicitly asks for one.

turmyshevd/openclawgotchi · 74 tokens

edit-soul