nanoclawbster: Skill for Claude Code

.claude/skills/update/SKILL.md

update is a skill for Claude Code from sskarz/nanoclawbster. It costs 46 tokens per session (1,483 once invoked), scanned C, a copy of update, MIT.

A skill for updating NanoClawbster from its upstream source while preserving custom changes and skills. It also runs migrations when needed.

In plain words
What is it for?
Use it to pull upstream changes, inspect the installation state, merge updates with customizations, and run required migrations.
Why use it?
It organizes the checks, fetch, merge, and migration work involved in updating an installation. It warns about uncommitted changes and pauses for confirmation before applying changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

This is sskarz/nanoclawbster's own configuration. It tells Claude Code how to work on nanoclawbster itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nanoclawbster configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sskarz/nanoclawbster. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sskarz/nanoclawbster/main/.claude/skills/update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sskarz/nanoclawbster

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 update

README.md
[![agentmods](https://agentmods.dev/badge/skills/sskarz/nanoclawbster/update/github.svg)](https://agentmods.dev/skills/sskarz/nanoclawbster/update)
Your own site
<a href="https://agentmods.dev/skills/sskarz/nanoclawbster/update"><img src="https://agentmods.dev/badge/skills/sskarz/nanoclawbster/update/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for update

Your own site · 80×15
<a href="https://agentmods.dev/skills/sskarz/nanoclawbster/update"><img src="https://agentmods.dev/badge/skills/sskarz/nanoclawbster/update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,483 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 95% copy Near-identical to another mod 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 $0.00046 $0.01483
Opus 5 $0.00023 $0.00741
Sonnet 5 $0.00009 $0.00297
Haiku 4.5 $0.00005 $0.00148

Measured 9d ago against content hash 2aa31b3e67a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

update scanned grade C with 1 finding 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch-upstream.sh), 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

If cancelled, clean up the temp dir (`rm -rf <TEMP_DIR>`) and stop.
Origin

This is a copy

95% identical to update — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/update/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update NanoClawbster

Pull upstream changes and merge them with the user's installation, preserving skills and customizations. Scripts live in .claude/skills/update/scripts/.

Principle: Handle everything automatically. Only pause for user confirmation before applying changes, or when merge conflicts need human judgment.

UX Note: Use AskUserQuestion for all user-facing questions.

1. Pre-flight

Check that the skills system is initialized:

test -d .nanoclawbster && echo "INITIALIZED" || echo "NOT_INITIALIZED"

If NOT_INITIALIZED: Run initSkillsSystem() first:

npx tsx -e "import { initNanoclawDir } from './skills-engine/init.js'; initNanoclawDir();"

Check for uncommitted git changes:

git status --porcelain

If there are uncommitted changes: Warn the user: "You have uncommitted changes. It's recommended to commit or stash them before updating. Continue anyway?" Use AskUserQuestion with options: "Continue anyway", "Abort (I'll commit first)". If they abort, stop here.

2. Fetch upstream

Run the fetch script:

./.claude/skills/update/scripts/fetch-upstream.sh

Parse the structured status block between <<< STATUS and STATUS >>> markers. Extract:

  • TEMP_DIR — path to extracted upstream files
  • REMOTE — which git remote was used
  • CURRENT_VERSION — version from local package.json
  • NEW_VERSION — version from upstream package.json
  • STATUS — "success" or "error"

If STATUS=error: Show the error output and stop.

If CURRENT_VERSION equals NEW_VERSION: Tell the user they're already up to date. Ask if they want to force the update anyway (there may be non-version-bumped changes). If no, clean up the temp dir and stop.

3. Preview

Run the preview to show what will change:

npx tsx scripts/update-core.ts --json --preview-only <TEMP_DIR>

This outputs JSON with: currentVersion, newVersion, filesChanged, filesDeleted, conflictRisk, customPatchesAtRisk.

Read the full file on GitHub · 172 lines

Files

What ships with it

1 file 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.

  1. 9d ago First seen · 172 lines · 46 tokens per session scan C 2aa31b3e67a2

Subscribe to this mod's changes

update is a skill published in the GitHub repository sskarz/nanoclawbster (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,483 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 95% identical to update, differing in 10 lines, and is treated as a copy.

Related

Other skills, from other repositories

hive-connect-repo

Register a repo with the server-side census sync: hive repo add writes the durable repo registry (the sync daemon picks it up on its next tick — no restart), private remotes authenticate via a token env var NAME (never a stored secret), and hivehealth(includecensushealth=true) verifies both that the sync daemon itself…

Hivemind-OSS/Hivemind · 150 tokens

github-multi-repo

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.

jazz-max/ruflo-hub · 21 tokens

create-worktree-skill

Use when the user explicitly asks for a SKILL to create a worktree. If the user does not mention "skill" or explicitly request skill invocation, do NOT trigger this. Only use when user says things like "use a skill to create a worktree" or "invoke the worktree skill". Creates isolated git worktrees with…

lroy-stack/ai-pod-store · 77 tokens

worktree-manager-skill

Comprehensive git worktree management. Use when the user wants to create, remove, list, or manage worktrees. Handles all worktree operations including creation, deletion, and status checking.

lroy-stack/ai-pod-store · 44 tokens

Hooks Automation

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

jazz-max/ruflo-hub · 46 tokens

version-bump

Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. NPM publishing is the final human-required handoff because the maintainer…

thedotmack/claude-mem · 64 tokens