#650 by GitHub stars
skills-directory/skill-codex
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/skill-codex/skills/codex/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
821a99b8ee16 → 821a99b8ee16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 821a99b8ee16
No earlier version was observed for comparison.
Verified commit 821a99b8ee166c23d621dd932a0a2a0cfdafd599
git clone --filter=blob:none --no-checkout https://github.com/skills-directory/skill-codex.git .hotskills/skills-directory-skill-codex && git -C .hotskills/skills-directory-skill-codex checkout --detach 821a99b8ee166c23d621dd932a0a2a0cfdafd599
# Copy each selected skill directory from .hotskills/skills-directory-skill-codex into .claude/skills/<skill-name>/Heat
3.9- Star growth, last 7 daysAhead of 61% of tracked repositories
- Star growth, last 24 hoursAhead of 3% of tracked repositories
- Rank movement, last 7 daysAhead of 39% of tracked repositories
- Commits, last 30 daysAhead of 70% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- codex
plugins/skill-codex/skills/codex
How it works
codex
When your agent uses it
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
2,143 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Running a Task
- Execution timeouts
- Following Up
- Critical Evaluation of Codex Output
- Error Handling
Files
../../../../.claude-plugin/marketplace.jsonasset780 bytes../../.claude-plugin/plugin.jsonasset596 bytesSKILL.mdcore8,740 bytesSKILL.mdcore8,740 bytes
Read SKILL.md
# Codex Skill Guide
## Running a Task
1. For a new session (resumes inherit the prior model/effort — see step 5), ask the user (via `AskUserQuestion`) which **model** AND which **reasoning effort** to use, in a **single prompt with two questions**. When the user expresses no preference, default to `gpt-6-astra` at `high`.
- **Model** — default `gpt-6-astra`:
- *GPT-6:* `gpt-6-astra` (frontier / most capable — **default**), `gpt-6.1-sol` (latest workhorse for coding and everyday work), `gpt-6-sol` (previous-generation workhorse), `gpt-6-luna` (fast & affordable, easier tasks)
- *GPT-5.6:* `gpt-5.6-sol` (reliable agentic workhorse), `gpt-5.6-terra` (balanced, everyday), `gpt-5.6-luna` (fast & affordable)
- *Legacy (rejected as unsupported when Codex is signed in with a ChatGPT account):* `gpt-5.5`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.3-codex-spark`, `gpt-5.3-codex`
- **Reasoning effort** — default `high`: `low`, `medium`, `high`, `xhigh`, `max`, `ultra`.
- `max`/`ultra` require a GPT-6 or GPT-5.6 model; `ultra` is only on `astra`/`sol`/`terra` (`luna` caps at `max`); legacy models cap at `xhigh`.
- `ultra` = maximum reasoning **with automatic task delegation** (slowest and most expensive — reserve for the hardest jobs).
- If the chosen effort exceeds the chosen model's maximum, fall back to that model's highest supported effort and tell the user.
2. Select the sandbox mode required for the task; default to `--sandbox read-only` unless edits or network access are necessary.
3. Assemble the command with the appropriate options:View the complete source on GitHubSkills included
- codex
Repository facts
- License
- MIT
- Created
- Oct 21, 2025
- Last pushed
- Oct 21, 2026
- Forks
- 118
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #650 · best #464 · down 90 in 30 days
- #642 on Oct 31
- #644 on Nov 1
- #647 on Nov 2
- #650 on Nov 3
- #651 from Nov 4 to Nov 5
- #650 since Nov 6
52 earlier periods
- #443 on Aug 2
- #451 on Aug 7
- #451 on Aug 9
- #466 on Aug 10
- #463 on Aug 11
- #459 on Aug 12
- #470 on Aug 13
- #465 on Aug 14
- #464 on Aug 17
- #474 on Aug 18
- #472 on Aug 19
- #477 on Aug 23
- #473 on Aug 26
- #488 on Aug 27
- #486 on Aug 28
- #480 on Aug 29
- #469 on Aug 30
- #491 on Aug 31
- #496 on Sep 1
- #500 on Sep 3
- #495 on Sep 6
- #499 on Sep 7
- #513 on Sep 8
- #505 on Sep 10
- #499 on Sep 12
- #514 on Sep 14
- #517 on Sep 17
- #518 on Sep 18
- #502 on Sep 19
- #516 on Sep 21
- #518 on Sep 23
- #508 on Sep 24
- #505 on Sep 25
- #539 on Sep 29
- #529 on Sep 30
- #516 on Oct 3
- #514 on Oct 4
- #524 on Oct 5
- #544 on Oct 7
- #560 on Oct 8
- #558 on Oct 9
- #547 on Oct 10
- #561 on Oct 13
- #566 on Oct 15
- #567 on Oct 16
- #578 on Oct 19
- #590 on Oct 21
- #578 on Oct 22
- #622 on Oct 25
- #633 on Oct 28
- #637 on Oct 29
- #639 on Oct 30
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
plugins/skill-codex/skills/codex/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 14 network referencesin 2 files: .claude-plugin/marketplace.json:1 plugins/skill-codex/.claude-plugin/plugin.json:5
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 14 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 5
"owner": { "name": "skills-directory", "url": "https://github.com/skills-directory" - Network accessline 6
"name": "skills-directory", "url": "https://github.com/skills-directory" }, - Network accessline 7
"url": "https://github.com/skills-directory" - Network accessline 14
"version": "1.3.1", "category": "development", "homepage": "https://github.com/skills-directory/skill-codex", - Network accessline 15
"category": "development", "homepage": "https://github.com/skills-directory/skill-codex", "tags": [ - Network accessline 16
"homepage": "https://github.com/skills-directory/skill-codex",
plugins/skill-codex/.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "skills-directory", "url": "https://github.com/skills-directory" - Network accessline 6
"name": "skills-directory", "url": "https://github.com/skills-directory" }, - Network accessline 7
"url": "https://github.com/skills-directory" - Network accessline 8
}, "homepage": "https://github.com/skills-directory/skill-codex", "repository": "https://github.com/skills-directory/skill-codex", - Network accessline 9
"homepage": "https://github.com/skills-directory/skill-codex", - Network accessline 10
"repository": "https://github.com/skills-directory/skill-codex",
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md plugins/skill-codex/skills/codex/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/skill-codex/skills/codex/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/skill-codex/skills/codex/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/skill-codex/skills/codex/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/skill-codex/skills/codex/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/skills-directory-skill-codex/)