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/shanggqm/codexu/codexu-releasenpx skills add shanggqm/codexU --skill codexu-releasegit clone --depth 1 https://github.com/shanggqm/codexUWrote 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/shanggqm/codexu/codexu-release)<a href="https://agentmods.dev/skills/shanggqm/codexu/codexu-release"><img src="https://agentmods.dev/badge/skills/shanggqm/codexu/codexu-release.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 | $0.00063 | $0.02327 |
| Opus 5 | $0.00032 | $0.01163 |
| Sonnet 5 | $0.00013 | $0.00465 |
| Haiku 4.5 | $0.00006 | $0.00233 |
Grade A, and why
codexu-release 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 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.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codexU Release SOP
Scope
Run this skill from the repository root. Treat the release as a real public publish: verify the current remote state first, keep unrelated user changes out of release commits, and report exactly what was built, pushed, and released.
Do not trust a remembered "latest" version. Always confirm the current tag and release state with GitHub before choosing the next version.
Preflight
- Inspect the worktree and branch:
git status --short
git branch --show-current
git remote -v
If unrelated files are dirty, do not stage or revert them. Either keep the release scoped to known release files or ask before mixing them into the release commit.
- Confirm GitHub access and current releases:
gh --version
gh auth status
gh repo view --json nameWithOwner,url
gh release list --limit 10
git fetch origin --tags
- Verify that the target
v<version>tag and GitHub Release do not already exist unless the task is explicitly to repair or replace them.
Mandatory Global Memory-Risk Gate
Run this gate before changing release metadata, packaging, committing, tagging, pushing, or creating a GitHub Release:
make memory-risk-check
sed -n '1,240p' build/memory-risk/report.md
The scan covers the entire production source tree, not only the release diff. Treat any non-zero exit as a hard release blocker. There is no override flag: fix or explicitly bound the risky lifecycle before continuing.
Do not accept the PASS line without reviewing the generated global inventory. Inspect every reported risk category and the related release diff, with particular attention to:
ProcessandPipe: bounded stdout reads with partial-response semantics for long-lived pipes, drained or redirected stderr, EOF handling, timeout, termination, and forced cleanup.Timer, notification/KVO observers, event monitors, and Combine subscriptions: weak captures and matching invalidation/removal/cancellation.- buffers, caches, samples, pending request maps, and static mutable collections: byte/count limits, eviction, timeout, and working-set release.
Data(contentsOf:)and transcript/session readers: trusted input boundaries, file-size checks, streaming behavior, and oversized-record handling.- recursive and parent-path traversal: explicit root/base termination, visited-node/path cycle guards, and regression coverage for platform-specific Foundation behavior.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 229 lines · 63 tokens per session scan A 2478255fab33
codexu-release is a skill published in the GitHub repository shanggqm/codexU (341 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 2,327 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
codex-review-loop
Adversarial PR code review using Codex CLI. Codex review (20-50 min) -> structured findings -> HITL approval -> fix loop.
project-conventions
Project code conventions reference. Covers typing, structure, DI, testing, and anti-pattern rules for module implementation.
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to…
openspec-context-docs
OpenSpec context documentation policy: keep requirements in spec.md and capture narrative context in context/overview/rationale docs under openspec/specs. Use when creating or updating OpenSpec docs, spec context, or onboarding/guide documentation.
codex-auth-setup
Install or refresh codex-multi-auth for the official Codex CLI, run first login, and verify account health and routing.
example
Example fixture skill for scanner regression coverage.