codex-coplan

codex-coplan is a skill for Claude Code, Codex from jiayx01/codex-claude-skills. It costs 92 tokens per session (808 once invoked), scanned A, original, MIT.

A planning aid for working with Codex, an external coding agent, by having both models draft plans independently, compare disagreements, and combine the results.

In plain words
What is it for?
Use it when the user explicitly mentions Codex and wants help preparing the brief, comparing plans, resolving differences, and merging them into one plan.
Why use it?
It helps produce a more considered implementation plan when two independent approaches are useful before coding begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it when the user explicitly mentions Codex and wants help preparing the brief, comparing plans, resolving differences, and merging them into one plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jiayx01/codex-claude-skills/codex-coplan
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jiayx01/codex-claude-skills --skill codex-coplan
Clone the repo
git clone --depth 1 https://github.com/jiayx01/codex-claude-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-coplan

README.md
[![agentmods](https://agentmods.dev/badge/skills/jiayx01/codex-claude-skills/codex-coplan.svg)](https://agentmods.dev/skills/jiayx01/codex-claude-skills/codex-coplan)
Your own site
<a href="https://agentmods.dev/skills/jiayx01/codex-claude-skills/codex-coplan"><img src="https://agentmods.dev/badge/skills/jiayx01/codex-claude-skills/codex-coplan.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.00808
Opus 5 $0.00046 $0.00404
Sonnet 5 $0.00018 $0.00162
Haiku 4.5 $0.00009 $0.00081

Measured 8d ago against content hash 0eaeb63eca33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

codex-coplan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/codex-coplan/SKILL.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Co-developing a plan with an external model

Process

  1. Prep the brief — Codex has no access to your conversation history, so assemble what it needs for this scenario: background and goals, hard constraints, judgment criteria, absolute paths to relevant files and directories (name the entry points and let it read them itself), what's already been tried and why it didn't work, and environmental facts (schema/API contracts/config values, scale, permissions, timeline — whatever applies). Look up what's missing yourself; only ask the user if you can't find it.

  2. Round one: independent drafts — write your own version, and dispatch Codex to write its own, with zero cross-reference on this round only: if both versions get pulled toward each other, there's no independent second opinion left to compare against. Give it nothing but the brief from step 1. For anything you already tried and know failed, state the reason (so it doesn't repeat the mistake); for anything you're just not satisfied with but haven't actually verified, give it only the label, no reasoning (a stated reason becomes an anchor). Assign it a plausible professional persona different from your own default framing (skip celebrities).

  3. Classify the differences (you do this yourself, don't dispatch it): agreements (both sides have it — goes straight into the plan), one-sided points (only one side has it), conflicts (same question, opposite answers).

  4. Follow upstarting this round, share your full draft with it, and keep the thread open from here on; the discussion needs to run on the same shared material going forward. Only follow up on one-sided points and conflicts, with specific questions — never "what do you think of the other version." Use --resume to continue the same thread, or it won't remember its own positions:

    • One-sided → "You didn't account for <approach>. Is it inapplicable, or did you miss it? If inapplicable, which constraint rules it out?"
    • Conflict → "You argued A, the other draft argued B — the disagreement comes down to an assumption about <something>. What's your assumption, and under what conditions does it break?"

Read the full file on GitHub · 25 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 25 lines · 92 tokens per session scan A 0eaeb63eca33

Subscribe to this mod's changes

codex-coplan is a skill published in the GitHub repository jiayx01/codex-claude-skills (4 stars, last pushed 27d ago), licensed MIT. It adds 92 tokens to every session and 808 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

deploy-from-stale-worktree-silent-rollback

Diagnose "I deployed a new Cloud Run / Docker image but a bunch of recently merged fixes regressed in production." Use when: (1) the deploy script does gcloud builds submit ... "${SCRIPTDIR}" or docker build (build context = local filesystem, NOT a git ref), (2) the user has many git worktrees / multiple checkouts of…

wan-huiyan/agent-traffic-control · 405 tokens

prep-pr-close-keyword-auto-closes-issue

Diagnose and prevent the trap where a scaffolding/prep/planning/handoff PR (one that ships a paste-ready prompt, an ADR, an implementation plan, or any docs-only artefact describing FUTURE work) contains a close-keyword like closes #N / fixes #N / resolves #N in its TITLE or BODY, which GitHub auto-applies at merge…

wan-huiyan/agent-traffic-control · 493 tokens

stale-base-pr-silently-reverts-upstream-content

Detect and recover when a sibling PR's squash-merge silently reverts an upstream PR's content changes because the sibling was based on a pre-upstream main snapshot and its line-level rewrites overlapped the upstream PR's edits. Use when: (1) two PRs are open in parallel against the same file(s) — one refreshing…

wan-huiyan/agent-traffic-control · 391 tokens

cross-worktree-spec-handoff-via-checkout-paths

Pass a shared file between two parallel sessions in different worktrees or branches, without merging to main first — a design spec, docs, a handoff prompt, a mockup. git checkout -- stages it. Use when a session says "the file doesn't exist". Not co editing.

wan-huiyan/agent-traffic-control · 79 tokens

docs-branch-off-feature-branch-smuggles-code

Catch the bug class where a "docs follow-up" PR silently ships the parent feature's code under a docs(sN): title because the docs branch was created from the current working branch (a feature branch), not from origin/main. Use when: (1) you just opened a PR titled docs(...) or chore(...) after wrapping up a feature…

wan-huiyan/agent-traffic-control · 454 tokens

gh-pr-merge-worktree-checkout-trap

Diagnose and bypass gh pr merge --squash --delete-branch failing with "failed to run git: fatal: 'main' is already used by worktree at ..." when another git worktree has main checked out. Use when: (1) you run gh pr merge and see this exact error, (2) you have multiple worktrees in the repo (e.g. .claude/worktrees/)…

wan-huiyan/agent-traffic-control · 497 tokens