troykelly/agent-development
external/skills/agent-development/SKILL.md
Use when the user wants to design Codex agent equivalents (specialized workers/profiles/prompt files), define triggering conditions, or build reusable agent prompts and validation tools.
$ install --global
skillsauthnpx skillsauth add troykelly/codex-skills agent-developmentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 11:50 PM4.5s7 files scanned
SKILL.md
- name:
- agent-development
- description:
- Use when the user wants to design Codex agent equivalents (specialized workers/profiles/prompt files), define triggering conditions, or build reusable agent prompts and validation tools.
Agent Development (Codex)
Overview
Codex CLI does not auto-discover "agent" files the way Claude plugins do. To recreate agent behavior in Codex, combine:
- Prompt files that define the agent's role and workflow.
- Codex config profiles to set model/sandbox/approval defaults.
- Skills that describe when to use the agent and how to launch it.
- Worker processes (
codex-subagent,codex exec, orworker-dispatch) for isolated execution.
This skill standardizes an agent card format (YAML frontmatter + prompt body) and shows how to run it with Codex.
Agent Card Format (Codex Convention)
Store agent prompts in agents/<agent-name>.md. Frontmatter is metadata for humans and validators; Codex does not read it automatically.
Required fields:
name(kebab-case identifier)description(when to use this agent)
Recommended fields:
profile(Codex config profile name)model(override model)sandbox_modeandapproval_policy(safety defaults)tools(advisory list of tools; use sandbox/approval to enforce)
Example:
---
name: pr-reviewer
description: Use this agent when the user asks for a code review or to audit a pull request.
profile: review-worker
model: gpt-5.2-codex
sandbox_mode: workspace-write
approval_policy: on-request
tools: ["Read", "Grep", "Bash"]
---
You are a senior PR reviewer...
Running an Agent
Preferred (subagent runner):
codex-subagent pr-reviewer <<'EOF'
[Provide task context and scope here.]
EOF
Fallback (manual codex exec):
awk 'BEGIN{c=0} /^---$/{c++; next} c>=2 {print}' agents/pr-reviewer.md | codex exec -p review-worker -
Profiles as Agent Defaults
Define per-agent profiles in ~/.codex/config.toml:
[profiles.review-worker]
model = "gpt-5.2-codex"
sandbox_mode = "workspace-write"
approval_policy = "on-request"
Profiles capture the model and safety settings that Claude agents used to embed in frontmatter.
Triggering (Codex Equivalent)
To make agent usage automatic, create a skill describing the trigger and invocation. The skill body should instruct how to run the agent card or spawn a worker.
Example trigger entry:
description: Use when the user asks for a PR review or code audit; run the pr-reviewer agent card.
See references/triggering-examples.md.
Validation
Use scripts/validate-agent.sh to validate agent cards for required fields and prompt length.
References
references/system-prompt-design.mdfor prompt structurereferences/triggering-examples.mdfor trigger phrasingreferences/agent-creation-system-prompt.mdfor AI-assisted agent card generationexamples/agent-creation-prompt.mdfor a complete prompt templateexamples/complete-agent-examples.mdfor full agent card examples
Related Skills
troykelly/worker-protocol
data-ai
VerifiedTrustedCommunity
Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.
6SKILL.mdUpdated Apr 15, 2026
troykelly/worker-handover
development
VerifiedTrustedCommunity
Defines context handover format when workers hit turn limit. Posts structured handover to GitHub issue comments enabling replacement workers to continue seamlessly.
6SKILL.mdUpdated Apr 15, 2026
troykelly/worker-dispatch
data-ai
VerifiedTrustedCommunity
Use to spawn isolated worker processes for autonomous issue work. Creates git worktrees, constructs worker prompts, and handles worker lifecycle.
6SKILL.mdUpdated Apr 15, 2026
troykelly/work-intake
tools
VerifiedTrustedCommunity
Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills. Use this when receiving any new work request.
6SKILL.mdUpdated Apr 15, 2026