Skills role-creator

📦

role-creator

Name: role-creator
Author: am-will

Content revision r1 Safe 📁 Filesystem access🔑 Env variables⚙️ External commands🌐 Network access

Create Codex Custom Agents

Custom Codex agents need precise TOML files and clear runtime settings. This skill guides role design, writes configs, and validates required fields.

Supports: Claude Codex Code(CC)

🥈 80 Silver

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "role-creator" from https://skillstore.io/skills/am-will-role-creator.md and its manifest at https://skillstore.io/api/skills/am-will-role-creator/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/am-will-role-creator.md Signed manifest GET /api/skills/am-will-role-creator/manifest Signed lockfile GET /api/skills/am-will-role-creator/lockfile

Test it

Using "role-creator". Create a reviewer role for one project.

Expected outcome:

A confirmed role name, description, model, reasoning level, and developer instruction set.
A project-scoped agent file path selected for the new role.
A validation result showing whether required fields are present.

Using "role-creator". Make a restricted research role.

Expected outcome:

A role profile with read-focused instructions and limited optional settings.
A reminder that stronger controls are only added after explicit user confirmation.

Using "role-creator". Troubleshoot an unknown agent type error.

Expected outcome:

A checklist for scope, file location, role name, and supported configuration keys.
Guidance to validate TOML syntax before changing behavior.

Security Audit

Safe

v8 • 7/9/2026 Open versioned report

Static alerts are false positives caused by expected Codex config paths, Markdown code formatting, documentation links, and quoted shell helper calls. I found no prompt injection attempt, credential exfiltration, covert network behavior, or malicious intent in the cited files. The scripts still edit local Codex configuration, so users should review paths before running them.

Files scanned

722

Lines analyzed

Review items

False positives ignored

Risk Factors

📁 Filesystem access (21)

🔑 Env variables (2)

references/role-config-reference.md:119 templates/full-role-config.toml:28

⚙️ External commands (44)

scripts/install_role.sh:53 scripts/install_role.sh:58 scripts/install_role.sh:71 scripts/install_role.sh:74 scripts/validate_role.sh:49 scripts/validate_role.sh:50 scripts/validate_role.sh:56 scripts/validate_role.sh:62 scripts/validate_role.sh:63 scripts/validate_role.sh:64 scripts/validate_role.sh:71 scripts/write_role_config.sh:141 scripts/write_role_config.sh:151 scripts/write_role_config.sh:155 scripts/write_role_config.sh:173 scripts/write_role_config.sh:188 scripts/write_role_config.sh:198 SKILL.md:14 SKILL.md:15 SKILL.md:17 SKILL.md:23 SKILL.md:24 SKILL.md:25 SKILL.md:26 SKILL.md:27 SKILL.md:28 SKILL.md:30 SKILL.md:38 SKILL.md:39 SKILL.md:40 SKILL.md:41 SKILL.md:42 SKILL.md:43 SKILL.md:45 SKILL.md:59 SKILL.md:60 SKILL.md:65-67 SKILL.md:67-71 SKILL.md:71-92 SKILL.md:92-96 SKILL.md:96-97 SKILL.md:97 SKILL.md:102-103 SKILL.md:103-104

🌐 Network access (2)

SKILL.md:102 SKILL.md:103

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/am-will-role-creator/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/am-will-role-creator/security.svg)](https://skillstore.io/skills/am-will-role-creator?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/am-will-role-creator?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/am-will-role-creator/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/am-will-role-creator.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

am-will. (2026). role-creator security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/am-will-role-creator/audits/8

BibTeX citation

@techreport{am-will-am-will-role-creator-2026,
  author = {am-will},
  title = {role-creator security audit report (audit version 8)},
  institution = {Skillstore},
  year = {2026},
  number = {8},
  url = {https://skillstore.io/skills/am-will-role-creator/audits/8},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "role-creator security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
  - name: "am-will"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/am-will-role-creator/audits/8"
identifiers:
  - type: other
    value: "skillstore:am-will-role-creator:audit:8"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create a project agent

Define a focused Codex agent for one repository with clear instructions and model settings.

Standardize team roles

Build repeatable agent profiles for review, research, planning, or implementation work.

Audit role configuration

Check that agent files use supported keys and include required role fields.

Try These Prompts

Create a basic role

Create a project Codex agent named reviewer. It should review pull requests for correctness and security. Use medium reasoning.

Add role details

Help me design a global Codex agent for backend incident analysis. Ask for any missing required values before writing the role file.

Update an existing role

Update my project reviewer agent to include nickname candidates and disabled web search. Validate the role after the change.

Build a constrained specialist

Create a read-focused architecture analyst role with workspace-write sandboxing, disabled network access, and strict developer instructions.

Best Practices

Confirm the role name, scope, model, reasoning effort, and instructions before writing files.
Keep generated roles minimal unless the user requests optional tools or permissions.
Validate TOML syntax and required keys after each create or update task.

Avoid

Do not add sandbox, web search, MCP, or app settings without explicit user approval.
Do not reuse vague developer instructions across unrelated roles.
Do not overwrite global Codex configuration without checking the intended scope.