openclaw-persona-forge

openclaw-persona-forge is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 43 tokens per session (918 once invoked), scanned B, original, Apache-2.0.

A generator for complete AI character identities, including personality descriptions, rules, names, and prompts for avatar images. It supports guided creation, random combinations, and refinement of an existing persona document.

In plain words
What is it for?
Use it to design personas for AI agents, write identity and boundary documents, choose names, and prepare avatar prompts.
Why use it?
It gives character-based AI agents a defined identity and boundaries instead of leaving their behavior unspecified. It also provides a structured way to revise an existing persona.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to design personas for AI agents, write identity and boundary documents, choose names, and prepare avatar prompts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jxoesneon/ciel/openclaw-persona-forge
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 jxoesneon/Ciel --skill openclaw-persona-forge
Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

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 openclaw-persona-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/openclaw-persona-forge/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/openclaw-persona-forge)
Your own site
<a href="https://agentmods.dev/skills/jxoesneon/ciel/openclaw-persona-forge"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/openclaw-persona-forge/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 openclaw-persona-forge

Your own site · 80×15
<a href="https://agentmods.dev/skills/jxoesneon/ciel/openclaw-persona-forge"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/openclaw-persona-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 918 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00918
Opus 5 $0.00022 $0.00459
Sonnet 5 $0.00009 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 9d ago against content hash 95e2a9ad5f63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

openclaw-persona-forge scanned grade B with 1 finding 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 9d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

5. **Avatar**: Fill 7 personalization variables, compose STYLE_BASE + description into prompt. If image skill available → auto-generate; else output prompt text for manual use (Gemini/ChatGPT/Midjourney). See `references
skills/openclaw-persona-forge/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.

CIEL ADAPTATION: OpenClaw Persona Forge

This skill generates complete AI agent personas — identity tension, soul description (SOUL.md), boundary rules, names, and avatar prompts. While originally built for OpenClaw's lobster-soul platform, the persona-generation pattern (identity × soul × rules × name × visual anchor) is reusable for any character-driven AI agent. The skill is pure generation — no network requests or file sending. Optional avatar image generation delegates to an environment-approved image skill.

Core Formula

A good persona = identity tension + boundary rules + personality flaws + name + visual anchor. All five must reinforce each other.

Modes

  • Guided mode: Present 10 archetype directions (fallen restart, peak boredom, misplaced life, etc.). User selects or mixes.
  • Gacha mode: python3 ${SKILL_DIR}/gacha.py [count] — true random from 8M combinations. Never improvise random — always run the script.
  • Refinement mode: User provides existing SOUL.md draft; skill fills gaps (name, rules, avatar prompt).

Generation Pipeline

  1. Direction: Select archetype or gacha-roll. Mix-and-match allowed (e.g., "archetype 2's boredom + archetype 7's veteran warmth").
  2. Identity tension: Past identity × current situation × inner contradiction → one-sentence soul. See references/identity-tension.md.
  3. Boundary rules: Derive 2-4 rules in the character's own voice — not generic clauses. See references/boundary-rules.md.
  4. Name: Provide 3 candidates with strategy type and pairing rationale. See references/naming-system.md.
  5. Avatar: Fill 7 personalization variables, compose STYLE_BASE + description into prompt. If image skill available → auto-generate; else output prompt text for manual use (Gemini/ChatGPT/Midjourney). See references/avatar-style.md.
  6. Output: Assemble complete persona, offer to write SOUL.md and IDENTITY.md files to user-specified directory.

Quality Criteria

Read the full file on GitHub · 63 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. 9d ago First seen · 63 lines · 43 tokens per session scan B 95e2a9ad5f63

Subscribe to this mod's changes

openclaw-persona-forge is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 43 tokens to every session and 918 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

surge

Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…

carbonshow/intent-fluid · 66 tokens

ai-native-software-dev

Use when the user asks to build, change, modernize, or reconstruct non-trivial software with an AI-native workflow, including greenfield development, work in an existing codebase, or authorized reference-based product reconstruction; also use when lifecycle planning, architecture, implementation, testing, review…

carbonshow/intent-fluid · 101 tokens

ticket-spec

Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.

watt-mind/factory · 45 tokens

Code Quality Review

Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.

asap-protocol/asap-protocol · 21 tokens

redpolicy-guide

An editorial policy for turning webinar transcripts into self-contained guides. A transcript is a written record of spoken material, while a self-contained guide can be understood without watching the webinar.

mikeshu2001/content-factory · 49 tokens

write-overview

A workflow for researching and writing a review essay about a project topic when no finished source text exists. It gathers the facts, studies example essays when available and produces the article in a project output folder.

mikeshu2001/content-factory · 17 tokens