NanoClaw Skill Payload Refresh

What it does

When your agent uses it

• After updating NanoClaw, when installed channel or provider code may be stale
• Refreshing only a few installed skills, such as slack and opencode
• Updating a fork where the official source is a separate upstream remote

Example prompts

• “Refresh all installed NanoClaw channel and provider skills after my update.”
• “Update only the slack and opencode payloads and show me the JSON result.”
• “My working tree has unrelated edits. Can I run the skill refresh now?”

Requirements

• A NanoClaw checkout with a clean git working tree
• pnpm and Git

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Preflight and selection
2. 2Treat the JSON result as a gate
3. 3Validate the composed checkout
4. 4Report

What it can do on your machine

Read from SKILL.md and the folder at commit af699e7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pnpm
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pnpm and git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

NanoClaw Skill Payload Refresh loads about 786 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 350 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~63

When it runs · the whole SKILL.md, loaded when a task matches

~786

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:9

  not re-run credential setup, change `.env`, alter wiring, or restart services.

• NoteMentions a .env fileSKILL.md:51

  t skips prompts, operator walkthroughs, `.env`

• NoteMentions a .env fileSKILL.md:70

  the source mode already selected in `.env`:

• NoteMentions a .env fileSKILL.md:73

  grep -q '^NANOCLAW_HARDENED_IMAGE=true$' .env 2>/dev/null; then

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nanocoai/nanoclaw at commit af699e7, republished under its MIT licence (© nanocoai). 350 words, ~786 tokens.

name

update-skills

description

Refresh installed NanoClaw channel and provider payloads from their registry branches with fork-safe remote resolution and a blocking structured result. Use after updating NanoClaw or whenever installed channel/provider code may be stale.

git status --porcelain

pnpm exec tsx scripts/update-skills.ts --skills all
# Example subset: --skills slack,opencode

pnpm run build
pnpm test

pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit

if grep -q '^NANOCLAW_HARDENED_IMAGE=true$' .env 2>/dev/null; then
  ./container/build.sh pull
else
  ./container/build.sh
fi

© nanocoai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/update-skills of nanocoai/nanoclaw.

Open the folder on GitHubat commit af699e7