cairn-loop-landing

cairn-loop-landing is a skill for Claude Code from cairn-framework/cairn. It costs 72 tokens per session (1,641 once invoked), scanned A, original, Apache-2.0.

A landing and merge procedure for one Cairn development-loop iteration. It handles putting the changes into one commit, opening a pull request, reviewing it, and merging it safely.

In plain words
What is it for?
Staging selected files, creating one squash commit, opening and reviewing a pull request, merging it, and re-running Cairn checks.
Why use it?
It gives the loop a controlled way to publish changes and stops without altering anything when the merge state or post-merge checks cannot be verified.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/cairn-framework/cairn/cairn-loop-landing
Any agent
npx skills add cairn-framework/cairn --skill cairn-loop-landing
Clone the repo
git clone --depth 1 https://github.com/cairn-framework/cairn

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 cairn-loop-landing

README.md
[![agentmods](https://agentmods.dev/badge/skills/cairn-framework/cairn/cairn-loop-landing.svg)](https://agentmods.dev/skills/cairn-framework/cairn/cairn-loop-landing)
Your own site
<a href="https://agentmods.dev/skills/cairn-framework/cairn/cairn-loop-landing"><img src="https://agentmods.dev/badge/skills/cairn-framework/cairn/cairn-loop-landing.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,641 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 5.1 $0.00072 $0.01641
Opus 5 $0.00036 $0.00821
Sonnet 5 $0.00014 $0.00328
Haiku 4.5 $0.00007 $0.00164

Measured 6d ago against content hash b83e1b229218, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cairn-loop-landing 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 6d 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.

.claude/skills/cairn-loop-landing/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cairn-loop-landing

Land one loop unit as exactly one squash commit on main, then merge it with fail-closed re-verification. This skill is the sole landing procedure for cairn-dev loop mode, which owns selection and the verdict table; this skill owns the publish-and-merge procedure and the terminal tokens a successful or failed landing returns.

Exit tokens

This skill declares the terminal tokens loop mode's End step keys on. It returns exactly one, as its final line:

  • ITERATION COMPLETE - the unit merged (or was safely deferred earlier; not this skill's path). On a clean merge, emit this.
  • LOOP HALTED - a fail-closed merge state the session cannot classify or clear: CLOSED-unmerged PR, unreadable PR state, a dirty tree at merge time, or the post-merge cairn scan --strict is non-zero. Touch nothing; report and halt.

Loop mode's End step passes the emitted token through verbatim.

Inputs

Always required (loop mode passes these in):

  • slug - the unit's branch tail: todo.<slug>, <finding-code>.<node>, or split.<slug> (the exact name loop mode's Isolation rule derived).
  • CAIRN - the bound cairn binary per loop mode's Repo bindings.

pr is path-dependent:

  • Normal Land (this skill creates the PR): do not pass pr. After gh pr create, capture the new PR number (gh pr view --json number --jq .number against the pushed head) and bind it for Cleanup.
  • Open-PR recovery (enters at Cleanup; the PR already exists): loop mode passes pr. Skip Land publish; go straight to Pre-submit review / Cleanup with the given pr.

Land: exactly one commit

Skip this section when entering at Cleanup (open-PR recovery).

If this unit had a change directory, run $CAIRN change apply <id> on the branch as its final task, then re-run $CAIRN scan --strict and $CAIRN hook all so the archived state is what gets verified; completion and archival land in the same commit.

Stage only the files the unit touched, by explicit path: source edits, tests, artefacts, and the paths apply moved or generated (read them from git status --short after apply; they are part of the unit).

Read the full file on GitHub · 139 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. 6d ago First seen · 139 lines · 72 tokens per session scan A b83e1b229218

Subscribe to this mod's changes

cairn-loop-landing is a skill published in the GitHub repository cairn-framework/cairn (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,641 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 2026-08-30.