lhc-update-agents

lhc-update-agents is a skill for Claude Code, Codex from megamen32/LastHumanCommit. It costs 103 tokens per session (953 once invoked), scanned A, original, MIT.

A controlled workflow for changing the source code of Last Human Commit, a project that tracks or marks the latest human-made commit. It requires changes to be made in the source repository and then deployed to supported coding-agent environments.

In plain words
What is it for?
Use it to update Last Human Commit's roles, protocols, templates, commands, adapters, or skills, then validate, commit, push, and roll out the changes.
Why use it?
It keeps edits, validation, commits, and installed copies coordinated. This reduces the risk of changing a deployed copy without updating the real source or leaving installations out of sync.

Skill for Claude CodeCodex

Part of the last-human-commit plugin — 12 skills, 5 hooks 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/megamen32/lasthumancommit/lhc-update-agents
Any agent
npx skills add megamen32/LastHumanCommit --skill lhc-update-agents
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 12 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.

agentmods badge for lhc-update-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/megamen32/lasthumancommit/lhc-update-agents.svg)](https://agentmods.dev/skills/megamen32/lasthumancommit/lhc-update-agents)
Your own site
<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/lhc-update-agents"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/lhc-update-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 953 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 $0.00103 $0.00953
Opus 5 $0.00051 $0.00477
Sonnet 5 $0.00021 $0.00191
Haiku 4.5 $0.00010 $0.00095

Measured 5d ago against content hash f999a4da1fab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lhc-update-agents 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.

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-update-agents/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rewrite Last Human Commit

Sources: /home/roomhacker/agents-projects/LastHumanCommit (git, main). This skill and lhc-rollout live canonically in the repo under skills/ and ship inside the LHC agent plugin. Never edit deployed copies under ~/.local/share/last-human-commit/ or project marker blocks directly — change the source, then roll out.

1. Baseline push — mandatory before edits

Make this bot's future changes identifiable as one commit range:

cd ~/agents-projects/LastHumanCommit
git status --porcelain   # must be empty; if dirty: review every path, repair blockers, commit the complete result
git log @{u}..HEAD       # must be empty; if not: push
git push origin main

The pushed HEAD is the baseline; everything after it belongs to this bot.

2. Edit sources and validate

  • Roles, protocols, templates, commands: src/common/; harness adapters: adapters/; skills: skills/ (keep the mirror under plugins/last-human-commit/skills/ byte-identical; sync harness-local copies such as ~/.zcode/skills/<name>).
  • Run python3 tests/validate.py and fix until green; never delete checks.

3. Commit and push after — unified history

Commit task-owned files at each completed step; at the end absorb reviewed foreign edits, leave the tree clean, and git push origin main.

4. Apply to every installed harness

Minimum set: zcode, codex, opencode, hermes (claude-code routers ride along). One machine-wide store per host: ~/.local/share/last-human-commit/current — no per-project .last-human-commit/ runtimes.

SKILL=~/agents-projects/LastHumanCommit/skills/lhc-rollout   # or ~/.zcode/skills/lhc-rollout
python3 $SKILL/scripts/lhc_rollout.py preview --manifest $SKILL/assets/last-human-commit-fleet.json > PREVIEW.json
confirmation=$(python3 -c 'import json,sys; print(json.load(open(sys.argv[1]))["confirmation"])' PREVIEW.json)
python3 $SKILL/scripts/lhc_rollout.py apply  --manifest $SKILL/assets/last-human-commit-fleet.json --confirm "$confirmation"
python3 $SKILL/scripts/lhc_rollout.py verify --manifest $SKILL/assets/last-human-commit-fleet.json

Read the full file on GitHub · 76 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. 5d ago First seen · 76 lines · 103 tokens per session scan A f999a4da1fab

Subscribe to this mod's changes

lhc-update-agents is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 953 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens