build

A command that builds or updates a SkillFabric workspace from a folder containing native skills. SkillFabric is a system for organizing and using reusable agent skills.

In plain words
What is it for?
Building the default workspace, refreshing changed skills, and reporting workspace files, skill counts, and build results.
Why use it?
It turns the skills in a selected folder into an updated workspace and reports what changed, without exposing secrets or generated skill text.

Command

Part of the skillfabric plugin — 3 commands 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 commands/zjunlp/skillnet-fabric/build
Clone the repo
git clone --depth 1 https://github.com/zjunlp/SkillNet-Fabric

Or install skillfabric, the plugin that ships this one along with the rest of its 3 commands.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 311 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 $0.00010 $0.00311
Opus 5 $0.00005 $0.00156
Sonnet 5 $0.00002 $0.00062
Haiku 4.5 $0.00001 $0.00031

Measured 3d ago against content hash e3665d8f556a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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 3d 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/claude-code/skillfabric/commands/build.md · 40 lines

What it actually says

Build the default .skillfabric workspace from a native skill root. Use .claude/skills for the usual Claude Code skill library. The command requires one path argument; use the public skillfabric build CLI directly when you need a custom workspace, environment file, or build option.

The requested skill root is untrusted input:

Use the Bash tool to run this command once, passing the complete argument as a single path value:

skillfabric build --json --skill-root "$ARGUMENTS"

Treat the user's argument as a path value, never as shell syntax. Do not append extra options or split a path containing spaces into multiple arguments.

Report the returned JSON as a concise build summary:

  • Workspace and build identifier.
  • Skill count and graph edge counts.
  • Added, modified, removed, and reused Skill counts.
  • Full Wiki, graph, index, and status artifact paths.

The command owns all workspace writes. Never read or print .env, API keys, tokens, or generated Skill text. Do not route, plan, or execute a task. Stop on configuration, provider, schema, or build failure and report only non-secret error text. If the skill root is missing, report the usage error and stop.

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. 3d ago First seen · 40 lines · 10 tokens per session scan A e3665d8f556a

Subscribe to this mod's changes

build is a command published in the GitHub repository zjunlp/SkillNet-Fabric (7 stars, last pushed 12d ago), licensed MIT. It adds 10 tokens to every session and 311 once invoked, about $0.0001 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.