agentmods.dev

openase: Skill for Codex

.codex/skills/push/SKILL.md

push is a skill for Codex from PacificStudio/openase. It costs 35 tokens per session (1,159 once invoked), scanned A, original, Apache-2.0.

A workflow for sending the current Git branch to GitHub and creating or updating its pull request, a request for code review.

In plain words
What is it for?
Use it when you need to push changes, publish updates, or create or update a pull request for OpenASE.
Why use it?
It combines the required checks with publishing the changes, reducing the chance of opening a pull request that fails project validation.

Skill for Codex

Written for Codex: installed under .codex/. Also seen: reads ~/.codex paths; mentions Codex.

This is PacificStudio/openase's own configuration. It tells Codex how to work on openase 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 openase configures →

not rated 269repo 2mo ago A scan SkillSpector: warn 35 tokens original Apache-2.0
View source ↗ PacificStudio/openase pacificstudio.ai
Reuse

Borrowing it

Nothing to install: this file belongs to PacificStudio/openase. 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/PacificStudio/openase/main/.codex/skills/push/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PacificStudio/openase

Made for: 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 push

README.md
[![agentmods](https://agentmods.dev/badge/skills/pacificstudio/openase/push/github.svg)](https://agentmods.dev/skills/pacificstudio/openase/push)
Your own site
<a href="https://agentmods.dev/skills/pacificstudio/openase/push"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/push/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 push

Your own site · 80×15
<a href="https://agentmods.dev/skills/pacificstudio/openase/push"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,159 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 98
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00035 $0.01159
Opus 5.5 $0.00014 $0.00464
Sonnet 5.5 $0.00007 $0.00232
Haiku 4.5 $0.00003 $0.00116

Measured 1mo ago against content hash 68129d5f76ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

push 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/openase_ci_gate.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.codex/skills/push/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Push

Prerequisites

  • gh CLI is installed and available in PATH.
  • gh auth status succeeds for GitHub operations in this repo.
  • corepack pnpm is available for frontend validation.

Goals

  • Push the current branch to origin safely.
  • Create a PR if none exists for the branch, otherwise update the existing PR.
  • Keep PR metadata aligned with the actual total scope of the branch.
  • Run the same local validation gates that current CI expects before publishing.
  • pull: use this when push is rejected or the branch must be merged with the latest origin/main.
  • commit: use this when there are local changes that are intended to ship but are not committed yet.

Validation Gate

Use the repo-local helper script:

  • .codex/skills/push/scripts/openase_ci_gate.sh

That script mirrors .github/workflows/ci.yml instead of asking the agent to guess which checks are needed:

  • Always runs make openapi-check because CI always runs API contract checks.
  • Detects go_changed and web_changed using the same path rules as CI.
  • Runs frontend CI with make web-install and corepack pnpm --dir web run ci when web_changed=true.
  • Runs backend and Go lint checks with make check, make build, LINT_BASE_REV=<base> make lint, make lint-depguard, and make lint-architecture when go_changed=true.

If the branch scope is ambiguous, use the script anyway; it already biases toward the stricter CI-compatible outcome.

Steps

  1. Identify the current branch and inspect working tree state.
  2. If there are intended but uncommitted changes, use the commit skill first.
  3. Ensure origin/main is available locally:
    • git fetch --no-tags origin main
  4. Run the local CI gate for the current branch diff:
    • .codex/skills/push/scripts/openase_ci_gate.sh
    • Use --plan first if you want to inspect which jobs it will run.
  5. Push the branch to origin, setting upstream tracking if needed.
  6. If the push is rejected because the remote moved:
    • Run the pull skill to merge origin/main and/or remote branch updates.
    • Rerun .codex/skills/push/scripts/openase_ci_gate.sh.
    • Push again.
    • Use --force-with-lease only when local history was intentionally rewritten.
  7. If the push fails due to auth, permissions, branch protection, or workflow restrictions, stop and surface the exact error. Do not rewrite remotes or switch protocols as a workaround.
  8. Ensure a PR exists for the branch:
    • If no PR exists, create one.
    • If a PR exists and is open, update it.
    • If the branch is tied to a closed or merged PR, create a new branch and a new PR instead of reusing stale history.
  9. Write a clear PR title that describes the shipped outcome, not just the last commit.
  10. Write or refresh the PR body explicitly. OpenASE does not currently require a repository PR template, so include concrete sections such as:
  • Summary
  • Validation
  • Risks / follow-up
  1. Reply with the PR URL from gh pr view.

Read the full file on GitHub · 140 lines

Files

What ships with it

1 file 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.

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. 1mo ago First seen · 140 lines · 35 tokens per session scan A 68129d5f76ea

Subscribe to this mod's changes

push is a skill published in the GitHub repository PacificStudio/openase (269 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,159 once invoked, about $0.0001 per session on Opus 5.5. 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.

Code reviewGit and workflowReleasesagentaisoftware-engineering
Related

Other skills, from other repositories

parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

suyoumo/ClawProBench · 67 tokens

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

github-automation

GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.

ruvnet/ruflo · 61 tokens

git

Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".

x-cmd/x-cmd · 58 tokens

meta-codereview-current-diff

Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.

opensquilla/opensquilla · 73 tokens

release

Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…

hyhmrright/brooks-lint · 135 tokens