Codex Prompt Engineering
Optimize Codex/GPT prompts for gpt-5.1, gpt-5.2, and gpt-5.2-codex with calibrated reasoning effort, autonomous execution patterns, correct tool contracts (apply_patch, exec_command, update_plan), compact outputs, evaluation flywheel loops, and production security controls.
Install
$ agentstack add skill-williamhallatt-cogworks-codex-prompt-engineering ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-williamhallatt-cogworks-codex-prompt-engineering) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Codex Prompt Engineering
> Knowledge snapshot: 2026-02-20
Purpose
Use this skill to design or review prompts for Codex/GPT coding agents with focus on:
- quality and reliability
- token efficiency
- correct tool usage
- safe autonomy
Use When
- Writing or revising system prompts for coding agents
- Debugging weak agent behavior (stalling, verbosity, bad tool calls)
- Calibrating
reasoning_effort(none|low|medium|high|xhigh) - Defining tool orchestration and planning behaviors
- Building evaluation loops for prompt iteration
Core Rules
- Calibrate reasoning effort
noneor omit for trivial formatting/retrievalmediumdefault for interactive codinghigh/xhighfor complex autonomous tasks
- Run end-to-end autonomously
- gather context -> plan -> implement -> test -> refine
- ask only for ambiguity, destructive actions, or major architecture trade-offs
- Use correct tool contracts
- file edits:
apply_patch - shell execution:
exec_command - task tracking:
update_planwithplan: [{step, status}] - batch independent calls with
multi_tool_use.parallel
- Keep communication compact
- tiny change: 2-5 sentences
- medium change: Measure -> Improve -> Repeat
- keep graders and representative datasets
- Apply security basics
- validate/sanitize untrusted inputs
- defend against direct/indirect prompt injection
- enforce least privilege for tools/data
Runtime Mapping Note
Some environments expose shell tools under different names. In this repository runtime:
- use
exec_command(notshell_command) - use
update_planschema:planwithstep/status
File Guide
reference.md: compact canonical guidance and checklistspatterns.md: reusable patterns beyond prompt engineeringexamples.md: concise before/after examples with correct contracts
Invocation
Use codex-prompt-engineering to review this prompt for quality and token efficiency.Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: williamhallatt
- Source: williamhallatt/cogworks
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.