codex

Name: codex
Author: jackspace

15stars7forks

How to install codex?

jackspace/claudeskillz/codex

$npx -y skills add jackspace/ClaudeSkillz --skill codex

Installs into the current project.

Summary

Executes OpenAI Codex CLI for code analysis, refactoring, and automated editing. Activates when users mention codex commands, code review requests, or automated code transformations requiring advanced reasoning models.

Files · 1

View on GitHub

SKILL.md

1	# Codex Execution Skill
2
3	## Prerequisites
4	- Codex CLI installed and configured (`~/.codex/config.toml`)
5	- Verify availability: `codex --version` on first use per session
6
7	## Workflow Checklist
8
9	For every Codex task, follow this sequence:
10
11	1. ☐ Detect HPC/Slurm environment:
12	- Check if running on HPC cluster (look for `/home/woody/`, `/home/hpc/`, Slurm env vars)
13	- If HPC detected: Always use `--yolo` flag to bypass Landlock sandbox restrictions
14
15	2. ☐ Ask user for execution parameters via `AskUserQuestion` (single prompt):
16	- Model: `gpt-5`, `gpt-5-codex`, or default
17	- Reasoning effort: `minimal`, `low`, `medium`, `high`
18
19	3. ☐ Determine sandbox mode based on task:
20	- `read-only`: Code review, analysis, documentation
21	- `workspace-write`: Code modifications, file creation
22	- `danger-full-access`: System operations, network access
23	- HPC override: Always add `--yolo` flag (bypasses Landlock restrictions)
24
25	4. ☐ Build command with required flags:
26	```bash
27	codex exec [OPTIONS] "PROMPT"
28	```
29	Essential flags:
30	- `-m <MODEL>` (if overriding default)
31	- `-c model_reasoning_effort="<LEVEL>"`
32	- `-s <SANDBOX_MODE>` (skip on HPC)
33	- `--skip-git-repo-check` (if outside git repo)
34	- `-C <DIRECTORY>` (if changing workspace)
35	- `--full-auto` (for non-interactive execution, cannot be used with --yolo)
36
37	HPC command pattern (with `--yolo` to bypass Landlock):
38	```bash
39	codex exec --yolo -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check \
40	"Analyze this code: $(cat /path/to/file.py)" 2>/dev/null
41	```
42
43	Note: `--yolo` is an alias for `--dangerously-bypass-approvals-and-sandbox` and is REQUIRED on HPC clusters to avoid Landlock sandbox errors. Do not use --full-auto with --yolo as they are incompatible.
44
45	5. ☐ Execute with stderr suppression:
46	- Append `2>/dev/null` to hide thinking tokens
47	- Remove only if user requests verbose output or debugging
48
49	6. ☐ Validate execution:
50	- Check exit code (0 = success)
51	- Summarize output for user
52	- Report errors with actionable solutions
53	- If Landlock/sandbox errors on HPC: verify `--yolo` flag was used, retry if missing
54
55	7. ☐ Inform about resume capability:
56	- "Resume this session anytime: `codex resume`"
57
58	## Command Patterns
59
60	> 🔥 HPC QUICK TIP: On HPC clusters (e.g., `/home/woody/`, `/home/hpc/`), ALWAYS add `--yolo` flag to avoid Landlock sandbox errors. Example: `codex exec --yolo -m gpt-5 ...`
61
62	### Read-Only Analysis
63	```bash
64	codex exec -m gpt-5 -c model_reasoning_effort="medium" -s read-only \
65	--skip-git-repo-check --full-auto "review @file.py for security issues" 2>/dev/null
66	```
67
68	### Stdin Input (bypasses sandbox file restrictions)
69	```bash
70	cat file.py \| codex exec -m gpt-5 -c model_reasoning_effort="low" \
71	--skip-git-repo-check --full-auto - 2>/dev/null
72	```
73	Note: Stdin with `-` flag may not be supported in all Codex CLI versions.
74
75	### HPC/Slurm Environment (YOLO Mode - Bypass Landlock)
76	When running on HPC clusters with Landlock security restrictions, use the `--yolo` flag:
77
78	```bash
79	# Primary solution: --yolo flag bypasses Landlock sandbox
80	codex exec --yolo -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check \
81	"Analyze this code: $(cat /path/to/file.py)" 2>/dev/null
82	```
83
84	Alternative: Manual Code Injection (if --yolo is unavailable):
85	```bash
86	# Capture code content and pass directly in prompt
87	codex exec -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check --full-auto \
88	"Analyze this Python code: $(cat file.py)" 2>/dev/null
89	```
90	Or for large files, use heredoc:
91	```bash
92	codex exec --yolo -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check "$(cat <<'ENDCODE'
93	Analyze the following code comprehensively:
94
95	$(cat file.py)
96
97	Focus on: architecture, algorithms, multi-GPU optimization, potential bugs, code quality.
98	ENDCODE
99	)" 2>/dev/null
100	```
101
102	Note: `--yolo` is short for `--dangerously-bypass-approvals-and-sandbox` and is safe on HPC login nodes where you have limited permissions anyway. Do not combine --yolo with --full-auto as they are incompatible.
103
104	### Code Modification
105	```bash
106	codex exec -m gpt-5 -c model_reasoning_effort="high" -s workspace-write \
107	--skip-git-repo-check --full-auto "refactor @module.py to async/await" 2>/dev/null
108	```
109
110	### Resume Session
111	```bash
112	echo "fix the remaining issues" \| codex exec --skip-git-repo-check resume --last 2>/dev/null
113	```
114
115	### Cross-Directory Execution
116	```bash
117	codex exec -C /path/to/project -m gpt-5 -c model_reasoning_effort="medium" \
118	-s read-only --skip-git-repo-check --full-auto "analyze architecture" 2>/dev/null
119	```
120
121	### Using Profiles
122	```bash
123	codex exec --profile production -c model_reasoning_effort="

People who liked this also viewed

6 picks

Type

hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026262k37k
request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026165k181k
analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026161k507
explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026161k507
ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026160k181k
scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026149k181k

codex

15stars7forks

View on GitHub

How to install codex?

jackspace/claudeskillz/codex

$npx -y skills add jackspace/ClaudeSkillz --skill codex

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Codex Execution Skill
2
3	## Prerequisites
4	- Codex CLI installed and configured (`~/.codex/config.toml`)
5	- Verify availability: `codex --version` on first use per session
6
7	## Workflow Checklist
8
9	For every Codex task, follow this sequence:
10
11	1. ☐ Detect HPC/Slurm environment:
12	- Check if running on HPC cluster (look for `/home/woody/`, `/home/hpc/`, Slurm env vars)
13	- If HPC detected: Always use `--yolo` flag to bypass Landlock sandbox restrictions
14
15	2. ☐ Ask user for execution parameters via `AskUserQuestion` (single prompt):
16	- Model: `gpt-5`, `gpt-5-codex`, or default
17	- Reasoning effort: `minimal`, `low`, `medium`, `high`
18
19	3. ☐ Determine sandbox mode based on task:
20	- `read-only`: Code review, analysis, documentation
21	- `workspace-write`: Code modifications, file creation
22	- `danger-full-access`: System operations, network access
23	- HPC override: Always add `--yolo` flag (bypasses Landlock restrictions)
24
25	4. ☐ Build command with required flags:
26	```bash
27	codex exec [OPTIONS] "PROMPT"
28	```
29	Essential flags:
30	- `-m <MODEL>` (if overriding default)
31	- `-c model_reasoning_effort="<LEVEL>"`
32	- `-s <SANDBOX_MODE>` (skip on HPC)
33	- `--skip-git-repo-check` (if outside git repo)
34	- `-C <DIRECTORY>` (if changing workspace)
35	- `--full-auto` (for non-interactive execution, cannot be used with --yolo)
36
37	HPC command pattern (with `--yolo` to bypass Landlock):
38	```bash
39	codex exec --yolo -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check \
40	"Analyze this code: $(cat /path/to/file.py)" 2>/dev/null
41	```
42
43	Note: `--yolo` is an alias for `--dangerously-bypass-approvals-and-sandbox` and is REQUIRED on HPC clusters to avoid Landlock sandbox errors. Do not use --full-auto with --yolo as they are incompatible.
44
45	5. ☐ Execute with stderr suppression:
46	- Append `2>/dev/null` to hide thinking tokens
47	- Remove only if user requests verbose output or debugging
48
49	6. ☐ Validate execution:
50	- Check exit code (0 = success)
51	- Summarize output for user
52	- Report errors with actionable solutions
53	- If Landlock/sandbox errors on HPC: verify `--yolo` flag was used, retry if missing
54
55	7. ☐ Inform about resume capability:
56	- "Resume this session anytime: `codex resume`"
57
58	## Command Patterns
59
60	> 🔥 HPC QUICK TIP: On HPC clusters (e.g., `/home/woody/`, `/home/hpc/`), ALWAYS add `--yolo` flag to avoid Landlock sandbox errors. Example: `codex exec --yolo -m gpt-5 ...`
61
62	### Read-Only Analysis
63	```bash
64	codex exec -m gpt-5 -c model_reasoning_effort="medium" -s read-only \
65	--skip-git-repo-check --full-auto "review @file.py for security issues" 2>/dev/null
66	```
67
68	### Stdin Input (bypasses sandbox file restrictions)
69	```bash
70	cat file.py \| codex exec -m gpt-5 -c model_reasoning_effort="low" \
71	--skip-git-repo-check --full-auto - 2>/dev/null
72	```
73	Note: Stdin with `-` flag may not be supported in all Codex CLI versions.
74
75	### HPC/Slurm Environment (YOLO Mode - Bypass Landlock)
76	When running on HPC clusters with Landlock security restrictions, use the `--yolo` flag:
77
78	```bash
79	# Primary solution: --yolo flag bypasses Landlock sandbox
80	codex exec --yolo -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check \
81	"Analyze this code: $(cat /path/to/file.py)" 2>/dev/null
82	```
83
84	Alternative: Manual Code Injection (if --yolo is unavailable):
85	```bash
86	# Capture code content and pass directly in prompt
87	codex exec -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check --full-auto \
88	"Analyze this Python code: $(cat file.py)" 2>/dev/null
89	```
90	Or for large files, use heredoc:
91	```bash
92	codex exec --yolo -m gpt-5 -c model_reasoning_effort="high" --skip-git-repo-check "$(cat <<'ENDCODE'
93	Analyze the following code comprehensively:
94
95	$(cat file.py)
96
97	Focus on: architecture, algorithms, multi-GPU optimization, potential bugs, code quality.
98	ENDCODE
99	)" 2>/dev/null
100	```
101
102	Note: `--yolo` is short for `--dangerously-bypass-approvals-and-sandbox` and is safe on HPC login nodes where you have limited permissions anyway. Do not combine --yolo with --full-auto as they are incompatible.
103
104	### Code Modification
105	```bash
106	codex exec -m gpt-5 -c model_reasoning_effort="high" -s workspace-write \
107	--skip-git-repo-check --full-auto "refactor @module.py to async/await" 2>/dev/null
108	```
109
110	### Resume Session
111	```bash
112	echo "fix the remaining issues" \| codex exec --skip-git-repo-check resume --last 2>/dev/null
113	```
114
115	### Cross-Directory Execution
116	```bash
117	codex exec -C /path/to/project -m gpt-5 -c model_reasoning_effort="medium" \
118	-s read-only --skip-git-repo-check --full-auto "analyze architecture" 2>/dev/null
119	```
120
121	### Using Profiles
122	```bash
123	codex exec --profile production -c model_reasoning_effort="

People who liked this also viewed

6 picks

Type