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 agentmods add skills/hyj28/claude-codex-pair/pairnpx skills add hyj28/claude-codex-pair --skill pairgit clone --depth 1 https://github.com/hyj28/claude-codex-pairWrote 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/hyj28/claude-codex-pair/pair)<a href="https://agentmods.dev/skills/hyj28/claude-codex-pair/pair"><img src="https://agentmods.dev/badge/skills/hyj28/claude-codex-pair/pair.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 | $0.00048 | $0.04795 |
| Opus 5 | $0.00024 | $0.02397 |
| Sonnet 5 | $0.00010 | $0.00959 |
| Haiku 4.5 | $0.00005 | $0.00479 |
Grade B, and why
pair scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
not be inherited from `~/.codex/config.toml`, where a temporary global `danger-full-access` How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pair — Claude plans, Codex implements, Claude reviews
You (Claude Code) are the orchestrator and reviewer. Codex CLI is the implementer,
invoked headlessly via codex exec — the user never copies context between terminals.
Arguments
/pair [fast|strict] <task description>
- First word
fastorstrictselects the profile; otherwise profile is standard. - Everything else is the task description.
| Profile | Plan handoff doc | Human plan approval | Run gate (Phase 4) | Claude review loop | Extra codex review |
|---|---|---|---|---|---|
| fast | no (one-paragraph instruction) | no | no | no | no |
| standard | yes | no | yes, when the change has a runtime surface | yes (max 2 rounds) | no |
| strict | yes | yes — wait for approval | yes; scenarios approved with the plan | yes (max 2 rounds) | yes (codex exec review) |
Preflight (all profiles)
- Verify this is a git repository (
git rev-parse --git-dir). If not, ask the user whether togit initor abort. - Verify
codexis on PATH. If not, stop and tell the user. - If the working tree has uncommitted changes, ask the user whether to proceed anyway (changes will get mixed into the new branch) or stop so they can commit/stash first.
- Note the current branch name — it is the base branch for diffs and review.
- Record the baseline. Detect the project's gate commands (see Phase 4) and run them
before handing anything to Codex. Write down, for each: the command, its exit code, and
the test runner's own count line (
42 passed,ok 17, …). Everything in Phase 4 is judged against this baseline, not against zero — otherwise a suite that was already red burns a fix round on someone else's debt, and a suite that silently collects no tests looks like success. If a runner reports no count, record "count unavailable" and say so in the final report; never substitute a guess.
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.
- 4d ago First seen · 340 lines · 48 tokens per session scan B 74ab012f027f
pair is a skill published in the GitHub repository hyj28/claude-codex-pair (4 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 4,795 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…