nebula: Skill for Claude Code

.claude/skills/land/SKILL.md

land is a skill for Claude Code from AgentSystemLabs/nebula. It costs 133 tokens per session (1,658 once invoked), scanned A, original, MIT.

A Git workflow for putting finished changes on the main branch through a branch, commit, push, pull request, review, merge, and return to an updated local checkout. Git tracks code changes, while a pull request is a proposed change for review.

In plain words
What is it for?
It helps prepare CI, create and push a branch, open and merge a pull request, respond to requested review comments, and fast-forward the local checkout.
Why use it?
Shared working folders can contain changes from other tasks, making broad staging or merging risky. This workflow checks the current state and limits the landing work to the relevant paths.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is AgentSystemLabs/nebula's own configuration. It tells Claude Code how to work on nebula 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 nebula configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AgentSystemLabs/nebula. 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/AgentSystemLabs/nebula/main/.claude/skills/land/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AgentSystemLabs/nebula

Made for: Claude Code.

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 land

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentsystemlabs/nebula/land.svg)](https://agentmods.dev/skills/agentsystemlabs/nebula/land)
Your own site
<a href="https://agentmods.dev/skills/agentsystemlabs/nebula/land"><img src="https://agentmods.dev/badge/skills/agentsystemlabs/nebula/land.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,658 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 unknown 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 $0.00133 $0.01658
Opus 5 $0.00067 $0.00829
Sonnet 5 $0.00027 $0.00332
Haiku 4.5 $0.00013 $0.00166

Measured today against content hash ebd4fcb3d517, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 today.

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.

.claude/skills/land/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A landing chore is seven commands. On 2026-09-04 a three-word "commit push and merge" took 17 minutes because the SELF-IMPROVING LOOP ran around it, and the user asked why. This skill is the refinement: no PROMPT DADDY rewrite, no MEMORY LOG entry unless something new bit you, no PROJECT TERMS pass. The reply is OUTPUT DOCTOR's short form — OVERVIEW and NEXT STEPS.

1. Read the situation — three commands, then decide the shape

git status --short && git branch --show-current && git rev-list --left-right --count HEAD...origin/main
gh pr view --json number,state,url,mergeStateStatus,headRefName 2>/dev/null   # a PR on this branch?
git diff --stat origin/main -- <the dirty paths>                                # is every hunk yours?
  • Dirty SHARED CHECKOUT on main ("commit push and merge") → shape A: branch, commit, push, PR, merge, fast-forward back. Only the paths the task touched — git add <paths>, never -A: other sessions' hunks are in this tree too (.claude/MEMORY.md, TERMS.md, gotchas.md are usually theirs as well as yours; take the file if your lines are in it, they ride along).
  • A branch with an open PR (a PR SESSION, "fix conflicts … babysit … merge") → shape B: bring origin/main in, answer the comments, wait for the check, merge.
  • "make pr" → shape A up to the pull request, then stop. When the third command's right-hand count is above zero and the moved paths overlap yours (git diff --stat HEAD...origin/main), merge origin/main first (§5) so the PR opens CLEAN, not CONFLICTING (2026-09-05: one commit into the same three memory files).

2. The gate — before anything leaves the machine

make ci (or make memory-check recall-eval terms-check when no crate changed), logged to the scratchpad — the GUARD HOOK blocks cargo … | tail. Red and not yours (git stash is blocked; prove it with git diff origin/main -- <file>) → say so and stop; do not push over a red gate.

3. Commit and push

git switch -c <kebab-branch>                      # from main; a worktree branch is already on one
git add <explicit paths>
git commit -F <scratchpad>/msg                    # never -m: backticks in "…" are command-substituted
git push -u origin <branch>

Read the full file on GitHub · 95 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. today First seen · 95 lines · 133 tokens per session scan A ebd4fcb3d517

Subscribe to this mod's changes

land is a skill published in the GitHub repository AgentSystemLabs/nebula (106 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 1,658 once invoked, about $0.0007 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 2026-09-06.