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.
npx agentmods add skills/cairn-framework/cairn/cairn-loop-landingnpx skills add cairn-framework/cairn --skill cairn-loop-landinggit clone --depth 1 https://github.com/cairn-framework/cairnWrote 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.
[](https://agentmods.dev/skills/cairn-framework/cairn/cairn-loop-landing)<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>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 5.1 | $0.00072 | $0.01641 |
| Opus 5 | $0.00036 | $0.00821 |
| Sonnet 5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
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.
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-mergecairn scan --strictis 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>, orsplit.<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. Aftergh pr create, capture the new PR number (gh pr view --json number --jq .numberagainst 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 givenpr.
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).
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.
- 6d ago First seen · 139 lines · 72 tokens per session scan A b83e1b229218
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.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…