A workflow for finishing an OpenASE pull request, a proposed code change that is reviewed before being merged. It syncs the branch, handles conflicts, waits for checks, addresses feedback, and squash-merges the change.

Use it to find the current branch’s pull request, run Go and Svelte validation, resolve conflicts with main, respond to reviews, and merge when ready.

It provides a defined path from an unfinished pull request to a mergeable one while keeping the project’s backend and frontend checks green.

land — Skill for Claude Code and Codex by PacificStudio: A workflow for finishing an OpenASE pull request, a…

Install

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.

agentmods

npx agentmods add skills/pacificstudio/openase/land

Any agent

npx skills add PacificStudio/openase --skill land

Clone the repo

git clone --depth 1 https://github.com/PacificStudio/openase

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pacificstudio/openase/land.svg)](https://agentmods.dev/skills/pacificstudio/openase/land)

Your own site

<a href="https://agentmods.dev/skills/pacificstudio/openase/land"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/land.svg" alt="Measured on agentmods" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,033 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00030	$0.01033
Opus 5	$0.00015	$0.00517
Sonnet 5	$0.00006	$0.00207
Haiku 4.5	$0.00003	$0.00103

Measured 4d ago against content hash 5f0481fbbe7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

land 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.

The scan reads SKILL.md. This mod also ships 1 executable file (land_watch.py), 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/land/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Land

Goals

Ensure the PR is conflict-free with origin/main.
Keep the current OpenASE validation and CI green.
Address human review feedback before merge.
Squash-merge the PR once checks pass.
Do not yield while the branch is mergeable and there is still concrete work to do.

Preconditions

gh CLI is authenticated.
You are on the PR branch with a clean working tree, or you are prepared to commit/push outstanding intended changes first.

Validation Gate

Use the repo's actual Go + Svelte checks instead of Symphony's Elixir flow.

Go/backend changes or unclear scope:
- PATH="$PWD/.tooling/go/bin:/home/yuzhong/.local/go1.26.1/bin:$PATH" go test ./...
- ./scripts/ci/lint.sh
Frontend changes under web/ or unclear scope:
- npm --prefix web install
- npm --prefix web run check
- npm --prefix web run build
Cross-cutting changes or uncertainty:
- Run all of the above before the final merge attempt.

Steps

Locate the PR for the current branch.
If the working tree has uncommitted intended changes, use the commit skill and then the push skill before proceeding.
Check mergeability and conflicts against origin/main.
If conflicts exist, use the pull skill to fetch and merge origin/main, resolve conflicts, rerun the applicable validation gate, then use the push skill to publish the updated branch.
Review outstanding feedback:
- Top-level PR comments
- Inline review comments
- Review summaries / CHANGES_REQUESTED
Before implementing review feedback, confirm it does not conflict with the task's intent. If you disagree, respond with concise rationale and only ask the user if product intent is genuinely ambiguous.
Reply to review threads before or alongside the corresponding code change so the record is clear.
Watch CI and review state until the PR is ready:
- Preferred: python3 .codex/skills/land/land_watch.py
- Fallback: gh pr checks --watch plus explicit review comment inspection with gh api.
If checks fail, inspect the failing run, fix the issue, rerun the applicable validation gate locally, commit, push, and restart the watch loop.
When all checks are green and outstanding feedback is resolved or answered, squash-merge using the PR title/body.

Read the full file on GitHub · 121 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.

land_watch.py 19 KB runs code

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.

4d ago First seen · 121 lines · 30 tokens per session scan A 5f0481fbbe7e

Subscribe to this mod's changes

land is a skill published in the GitHub repository PacificStudio/openase (265 stars, last pushed 25d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,033 once invoked, about $0.0002 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.

Git and workflow agent ai software-engineering

aisee:init

初始化、审计并优化 OpenSpec/Aisee 项目配置。仅适用于已使用或准备接入 OpenSpec 的项目；用于创建或修复 AGENTS.md、openspec/project.md、aisee/memory/、最小 Aisee docs 目录，并在当前支持的 Codex hook target 下安装项目级 hooks；检查 hook 机制兼容性、OpenSpec 状态机、baseline 迁移入口与项目技术架构边界。触发词包括 aisee:init、aisee-init、初始化项目配置、优化 AGENTS.md、配置 Codex hooks、OpenSpec 配置审计。.

AISEE-LAB/aisee-plugin · 134 tokens

aisee:srs

通过结构化对话充分澄清软件类业务需求，并生成规划级详细的需求规格说明书（SRS）。当用户想写需求文档、澄清产品范围、整理业务目标/用户角色/业务能力/业务流程/业务规则/权限/非目标，或为 aisee:change-plan 准备稳定输入时使用。适用于 App、小程序、Web、桌面软件、后端/API 服务、CLI 工具、定时任务/异步任务等软件项目。SRS 应写到足够支持后续拆 change 和编写 change 内容，但不要写成接口设计、数据库设计、技术方案、视觉设计、硬件架构、固件设计或开发任务。.

AISEE-LAB/aisee-plugin · 159 tokens

land