task-land

task-land is a skill for Claude Code, Codex from loncadev/baron. It costs 73 tokens per session (1,290 once invoked), scanned A, original, Apache-2.0.

A Baron workflow for landing a pull request, meaning taking it out of draft status and merging it after approval.

In plain words
What is it for?
Merge an approved work-item pull request through Baron's source-control workflow.
Why use it?
It checks the pull request's automated checks before merging, reducing the chance of merging unfinished or failing code.

Skill for Claude CodeCodex

Part of the baron plugin — 10 skills shipped together

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/loncadev/baron/task-land
Any agent
npx skills add loncadev/baron --skill task-land
Clone the repo
git clone --depth 1 https://github.com/loncadev/baron

Made for: Claude Code, Codex.

Or install baron, the plugin that ships this one along with the rest of its 10 skills.

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 task-land

README.md
[![agentmods](https://agentmods.dev/badge/skills/loncadev/baron/task-land.svg)](https://agentmods.dev/skills/loncadev/baron/task-land)
Your own site
<a href="https://agentmods.dev/skills/loncadev/baron/task-land"><img src="https://agentmods.dev/badge/skills/loncadev/baron/task-land.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,290 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.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.01290
Opus 5 $0.00036 $0.00645
Sonnet 5 $0.00015 $0.00258
Haiku 4.5 $0.00007 $0.00129

Measured 3d ago against content hash e9edde86db1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-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 3d 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.

plugins/claude-code/skills/task-land/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Land a task (merge the PR)

The last mile of the daily loop: task-new → task-start → task-finish → **task-land**. One deterministic recipe call does the whole landing — undraft, then merge.

Never fall back to gh pr merge / az repos pr update. Baron has the primitives, and going around it means the merge happens outside the run the user can audit. If Baron refuses, the refusal is the answer — report it, don't route around it.

Steps

  1. Identify the work item: parse the current branch (git rev-parse --abbrev-ref HEAD) as <prefix>/<id>-<slug>. If the branch doesn't match, ask which item to land — never merge a PR you inferred.

  2. Check before you merge — call baron_scm_read op=pr_for_branch, then baron_scm_read op=pr_status on the PR it returns. Read three things and say them out loud:

    • checks (rollup) — failed or pending means STOP and ask, rather than merging red or unfinished. unknown means the view was incomplete, and checks.unreadable names exactly which sources did not contribute — quote it. ['check-runs', 'actions-runs'] means the credential lacks Actions: Read (a fine-grained GitHub token can never hold the Checks permission, so Actions is the way in); ['policy-evaluations'] is Azure, which Baron does not read yet. This matters: an unexplained unknown looks like a broken integration, and someone will go hunting. It is NOT none — that one means the provider was asked and there is genuinely no CI.

      Do not conclude Baron is broken by comparing against gh: the GitHub CLI authenticates with a different, broader credential than Baron's token, so it routinely sees checks Baron's token may not. Compare permissions, not tools.

    • reviewDecisionchanges_requested means STOP. review_required is the user's call.

    • mergeable — false usually means conflicts; the fix is a local rebase, not a retry.

    If anything is red or ambiguous, ask with AskUserQuestion before proceeding. A merge is hard to take back.

  3. Ask how it should land (AskUserQuestion, one question, only if the user didn't already say): "Merge strategy?"Squash / Merge commit / Rebase / Provider default. Offer deleting the source branch in the same question if the repo doesn't do it automatically.

  4. Run the recipe — call baron_recipe_run exactly once:

Read the full file on GitHub · 84 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. 3d ago First seen · 84 lines · 73 tokens per session scan A e9edde86db1d

Subscribe to this mod's changes

task-land is a skill published in the GitHub repository loncadev/baron (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,290 once invoked, about $0.0004 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.