codex-first
Route implementation work to Codex CLI; Claude specs, reviews, verifies.
Skill by Khang5687
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/khang5687-codex-first
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/codex-first
What's inside
- Skill name
codex-first- Description
- Route implementation work to Codex CLI; Claude specs, reviews, verifies.
- License
- MIT
- Instructions
- 73 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Codex First
Claude Code sessions only. Codex/other harnesses: skip; never self-delegate.
Rationale: Claude (Fable/Opus) tokens metered + expensive; Codex flat-rate. GPT-5.5+ is usually the better and faster model at writing/implementing code; Claude wins at ergonomics — judgment, design, spec-writing, review, orchestration. So Codex types, Claude thinks and verifies.
## Route
Delegate to Codex (default for hands-on work):
- implementation from a frozen spec; refactors; mechanical migrations
- bug fixes with known repro; test writing; coverage fills
- CI fixes, dependency bumps, scripts/tooling
- bulk codebase exploration where raw reading ≫ the answer
Keep in Claude:
- design, API design, architecture, naming, UX judgment
- tasks where writing the spec IS the work (ambiguity = design)
- tiny edits (~<20 lines, single obvious change) — delegation overhead loses
- anything needing session tools: MCP (browser/computer-use/chronicle), 1Password, secrets
- destructive/irreversible ops, releases, pushes, GitHub mutations — Claude-side per git rules
- review of Codex output — never delegated, never skipped
Mixed task: Claude designs first, freezes spec, delegates build-out.
Heuristic: prompt reads as a work order → delegate; writing it forces decisions → design, Claude.
Portfolio/multi-repo work: `$maintainer-orchestrator` instead.
## Invoke
Prompt via temp file, never inline quoting:
```bash
P=$(mktemp); cat >"$P" <<'EOF'
<goal, repo + key paths, constraints ("don't touch X"), non-goals, proof expected, output shape>
EOF
command codex exec --yolo -C <repo> \
-c model_reasoning_effort="high" \
-o /tmp/codex-last.md - <"$P" 2>/dev/null
```
- `--yolo` is the house default; Codex may run commands/tests freely. Keep prompts scoped to the target repo.
- `command codex` bypasses the interactive zsh wrapper; if not on PATH: `fnm exec --using default -- codex`
- stderr suppressed (thinking noise bloats context); drop `2>/dev/null` only to debug a failing run
- read `-o` file for the result; don't parse the JSONL stream
- long runs: Bash run_in_background, read `-o` file on exit; don't kill quiet runs <30 min
- parallel independent tasks OK: separate repos/dirs, separate `-o` files
- outside a git repo add `--skip-git-repo-check`
Follow-up fixes — cheaper than fresh runs, keeps context. `resume` has no `-C`/`--yolo`: run from the repo dir, spell the long flag:
```bash
(cd <repo> && command codex exec resume --last \
--dangerously-bypass-approvals-and-sandbox \
-o /tmp/codex-last.md - <"$P2" 2>/dev/null)
```
## Prompt contract
Codex starts with zero session context. Every prompt: goal, exact repo/paths, constraints, non-goals, proof expected (exact test command), output shape ("report files changed + test output"). Spec quality decides success.
## Verify (Claude, always)
- `git status -sb` + read the full diff; judge like a contributor PR
- run focused tests yourself or demand proof output; Codex claims are advisory
- iterate via resume; after 2 failed rounds, take over and do it directly
- normal closeout still applies: `$autoreview` before ship
## Economics
Win = generation + exploration tokens moved to Codex; Claude spends only on spec + diff review. Don't ping-pong trivia through delegation; don't re-read what Codex already summarized.From Khang5687/agent-scripts, MIT.
More from Khang5687/agent-scripts
- 0.570score
delegate-to-other-agents
Khang5687
Route implementation work to flat-rate executors (Codex CLI, Grok CLI) or Claude subagents; Claude specs, reviews, verifies.
SkillAFreshness: AClaude Code +9 - 0.567score
clone-website
Khang5687
Rebuild existing web pages as working local code, matching their real content, assets, responsive layout, and interactions.
SkillAFreshness: AClaude Code +9 - 0.567score
agent-broker
Khang5687
Use for Netlify, Vercel, Supabase or Apify work (deploys, logs, SQL, migrations, actors), API tokens or .env secrets, Docker Compose secrets on a Linux…
SkillAFreshness: AClaude Code +9 - 0.520score
bible-history-verifier-sift
Khang5687
Activate automatically for queries about historical context, biblical events, claim verification, SIFT analysis or bible history.
SkillBFreshness: BClaude Code +9 - 0.473score
agent-transcript
Khang5687
GitHub PR/issue agent transcripts: redact, preview, and insert safely.
SkillCFreshness: CClaude Code +9 - 0.469score
delegation-status
Khang5687
Show who's been doing the delegated work: executor/subagent/kept-in-Claude breakdown, accounts, outcomes, recent tasks.
SkillCFreshness: CClaude Code +9 - 0.469score
browser-use
Khang5687
Existing Chrome automation: Chrome plugin first, mcporter fallback.
SkillCFreshness: CClaude Code +9 - 0.469score
github-cache-hygiene
Khang5687
GitHub quota/cache hygiene: gh, ghx, xcache, gitcrawl, mirrors, limits.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 5, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Khang5687/agent-scripts
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Khang5687
- 0.570score
delegate-to-other-agents
Khang5687
Route implementation work to flat-rate executors (Codex CLI, Grok CLI) or Claude subagents; Claude specs, reviews, verifies.
SkillAFreshness: AClaude Code +9 - 0.567score
clone-website
Khang5687
Rebuild existing web pages as working local code, matching their real content, assets, responsive layout, and interactions.
SkillAFreshness: AClaude Code +9 - 0.567score
agent-broker
Khang5687
Use for Netlify, Vercel, Supabase or Apify work (deploys, logs, SQL, migrations, actors), API tokens or .env secrets, Docker Compose secrets on a Linux…
SkillAFreshness: AClaude Code +9 - 0.520score
bible-history-verifier-sift
Khang5687
Activate automatically for queries about historical context, biblical events, claim verification, SIFT analysis or bible history.
SkillBFreshness: BClaude Code +9 - 0.473score
agent-transcript
Khang5687
GitHub PR/issue agent transcripts: redact, preview, and insert safely.
SkillCFreshness: CClaude Code +9 - 0.469score
delegation-status
Khang5687
Show who's been doing the delegated work: executor/subagent/kept-in-Claude breakdown, accounts, outcomes, recent tasks.
SkillCFreshness: CClaude Code +9
Cite this page
codex-first skill. Agent Mart. https://agentmart.dev/skills/khang5687-codex-first (last updated 2026-10-24)