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.
npx skills add jiayx01/codex-claude-skills --skill codex-coplangit clone --depth 1 https://github.com/jiayx01/codex-claude-skillsWrote 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.
[](https://agentmods.dev/skills/jiayx01/codex-claude-skills/codex-coplan)<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>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.
| Model | Per session | Once 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 |
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.
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
-
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.
-
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).
-
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).
-
Follow up — starting 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
--resumeto 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?"
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.
- 8d ago First seen · 25 lines · 92 tokens per session scan A 0eaeb63eca33
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 $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
deploy-from-stale-worktree-silent-rollback
Diagnose "I deployed a new Cloud Run / Docker image but a bunch of recently merged fixes regressed in production." Use when: (1) the deploy script does gcloud builds submit ... "${SCRIPTDIR}" or docker build (build context = local filesystem, NOT a git ref), (2) the user has many git worktrees / multiple checkouts of…
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…
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…
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.
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…
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/)…