A procedure for distributing a versioned Last Human Commit release to local computers and remote machines over SSH.

It helps preview and apply releases, switch active versions atomically, preserve routing markers, roll back when needed, and verify file digests.

It helps prevent accidental or inconsistent rollouts by previewing targets, requiring confirmation, and checking the result afterward.

lhc-rollout — Skill for Claude Code and Codex by megamen32: A procedure for distributing a versioned Last Human Commit…

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/megamen32/lasthumancommit/lhc-rollout

Any agent

npx skills add megamen32/LastHumanCommit --skill lhc-rollout

Clone the repo

git clone --depth 1 https://github.com/megamen32/LastHumanCommit

Made for: Claude Code, Codex.

Or install last-human-commit, the plugin that ships this one along with the rest of its 20 skills, 5 hooks.

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/megamen32/lasthumancommit/lhc-rollout.svg)](https://agentmods.dev/skills/megamen32/lasthumancommit/lhc-rollout)

Your own site

<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/lhc-rollout"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/lhc-rollout.svg" alt="Measured on agentmods" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 667 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 5.1	$0.00087	$0.00667
Opus 5	$0.00044	$0.00333
Sonnet 5	$0.00017	$0.00133
Haiku 4.5	$0.00009	$0.00067

Measured 5d ago against content hash 43702bc10256, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

lhc-rollout 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/lhc_rollout.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.

plugins/last-human-commit/skills/lhc-rollout/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LHC Rollout

Use the bundled deterministic script. Do not rediscover or rewrite the rollout procedure in the prompt.

Workflow

Require a committed source revision and an explicit Fleet manifest. When creating or changing the manifest, read references/manifest.md. For the current 100/44/88/Mac topology, use assets/last-human-commit-fleet.json; do not rediscover that matrix.

Run preview:

python3 scripts/lhc_rollout.py preview --manifest MANIFEST.json > PREVIEW.json

Check the version, digest, exact targets, actions, and rollback paths. Stop on a missing target, freshness conflict, immutable-version collision, or unresolved router role reference.

If the user's request already authorizes rollout, apply the exact preview:

confirmation=$(python3 -c 'import json,sys; print(json.load(open(sys.argv[1]))["confirmation"])' PREVIEW.json)
python3 scripts/lhc_rollout.py apply --manifest MANIFEST.json --confirm "$confirmation"

Otherwise return the preview and wait. Never manufacture or reuse a stale confirmation.

Verify independently:

python3 scripts/lhc_rollout.py verify --manifest MANIFEST.json

Run one physical harness canary that reads the installed router or role file. Do not substitute provider, logs, DB, Grafana, permissions, or secret checks for LHC delivery.

Machine-wide store

One LHC store per host: ~/.local/share/last-human-commit/current. Project routers reference the machine store absolutely; per-project .last-human-commit/ runtimes are legacy — remove them after routers are re-pointed. One apply per version: a rollback receipt for version X blocks re-applying X; push a new commit to create a new version. Freshness windows (~5 minutes) protect files a rollout just touched — wait them out, don't force.

Source of truth

Canonical: ~/agents-projects/LastHumanCommit/skills/lhc-rollout (repo, main branch).
Mirrors: the LHC plugin package skills/lhc-rollout/ and harness-local copies such as ~/.zcode/skills/lhc-rollout.
Never hand-edit a mirror; change the repo, then redeploy. The rollout manifest contains no credentials.

Read the full file on GitHub · 69 lines

Files

What ships with it

3 files 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.

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.

5d ago First seen · 69 lines · 87 tokens per session scan A 43702bc10256

Subscribe to this mod's changes

lhc-rollout is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 667 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.

DevOps and cloud Git and workflow Releases

agent-release-swarm

Agent skill for release-swarm - invoke with $agent-release-swarm.

ruvnet/ruflo · 19 tokens

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.

paperclipai/paperclip · 42 tokens

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.

openai/symphony · 42 tokens

changelog

Create changelog files for important commits in a PR.

pipecat-ai/pipecat · 13 tokens

multi-agent-release-manager

Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.

chromium/chromium · 27 tokens

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…

Azure/azure-sdk-for-net · 91 tokens