codex-in-claude: Skill for Claude Code

.agents/skills/working-an-issue/SKILL.md

working-an-issue is a skill for Claude Code from briandconnelly/codex-in-claude. It costs 105 tokens per session (1,133 once invoked), scanned A, original, MIT.

A guided workflow for taking a GitHub issue from selection to a ready pull request. It sequences planning, implementation, reviews, and human approval points.

In plain words
What is it for?
Use it to pick and claim an issue, verify and plan the work, implement it, request Codex and Copilot reviews, open the pull request, and hand it off for merging.
Why use it?
It keeps issue work in the intended order and makes required checks and handoffs easier to follow.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is briandconnelly/codex-in-claude's own configuration. It tells Claude Code how to work on codex-in-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-in-claude configures →

Part of the codex-in-claude plugin — 8 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to briandconnelly/codex-in-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/briandconnelly/codex-in-claude/main/.agents/skills/working-an-issue/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/briandconnelly/codex-in-claude

Made for: Claude Code.

Or install codex-in-claude, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

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 working-an-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/briandconnelly/codex-in-claude/working-an-issue/github.svg)](https://agentmods.dev/skills/briandconnelly/codex-in-claude/working-an-issue)
Your own site
<a href="https://agentmods.dev/skills/briandconnelly/codex-in-claude/working-an-issue"><img src="https://agentmods.dev/badge/skills/briandconnelly/codex-in-claude/working-an-issue/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for working-an-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/briandconnelly/codex-in-claude/working-an-issue"><img src="https://agentmods.dev/badge/skills/briandconnelly/codex-in-claude/working-an-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,133 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 $0.00105 $0.01133
Opus 5 $0.00053 $0.00566
Sonnet 5 $0.00021 $0.00227
Haiku 4.5 $0.00011 $0.00113

Measured 10d ago against content hash a98d77d340d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

working-an-issue 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 10d 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.

.agents/skills/working-an-issue/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working an issue

Orchestrates the issue → green-PR lifecycle in this repo. This skill owns the order of operations and the human checkpoints; every rule lives in AGENTS.md (auto-loaded each session), with named helper skills supplying the mechanism where a step needs one.

Scope & dependencies. Harness-neutral, but not capability-free. Run this skill only in an agent session that has loaded this repo's AGENTS.md, can pause at the maintainer checkpoints, can operate Git/GitHub, and can invoke a separate Codex process or integration that preserves the readiness, redaction, spend, and verify safeguards of collaborating-with-codex. Preferred helper in Claude Code: collaborating-with-codex (bundled with this plugin). Optional review-disposition helper: receiving-code-review (an external Superpowers plugin). When a helper skill is absent, use the fallback its phase names; AGENTS.md stays authoritative for every rule.

How to read a phase: each phase names an action and cites the AGENTS.md § section that owns the rule (and, where a step needs one, a helper skill as the mechanism). Open the cited section and follow it — this file deliberately does not restate the rule, so acting on a phase line alone will miss it.

Before you start: verification honesty

Run every check a phase prescribes — never predict its result. Local inspection (git show, the working tree) proves neither a push nor a merge — it only shows a local object. Before claiming something is pushed, compare the remote ref (git rev-parse origin/<branch> or git ls-remote origin <branch>); before claiming it is merged, query the PR or default branch (gh pr view <n> --json state,mergedAt, or confirm origin/main contains the commit).

Phases

Work them in order. ▸ marks a phase that pauses for the maintainer.

  1. Select & claim ▸ — Pick the most important open, unassigned issue, then run the claim protocol. Rules: AGENTS.md § Git / PRs (claiming) and § Agent identity (why a bot can't self-assign). Checkpoint: confirm the issue choice with the maintainer before claiming.

Read the full file on GitHub · 60 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. 10d ago First seen · 60 lines · 105 tokens per session scan A a98d77d340d2

Subscribe to this mod's changes

working-an-issue is a skill published in the GitHub repository briandconnelly/codex-in-claude (3 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,133 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.