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.
npx agentmods add commands/rolecraft-sh/rolecraft/bundlegit clone --depth 1 https://github.com/rolecraft-sh/rolecraftWhat 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 | $0.00000 | $0.00463 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
bundle 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 2d 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.
What it actually says
rolecraft bundle
Install multiple skills at once from inline sources or a bundle file.
Usage
rolecraft bundle <sources...> # install inline sources
rolecraft bundle <file> # install from a bundle file
rolecraft bundle create [<name>] # create a new bundle file
Inline sources
Pass multiple sources as arguments:
rolecraft bundle owner/react-patterns owner/ts-practices ./css-layout
rolecraft bundle owner/skill1 owner/skill2 --dry-run # preview only
From a file
JSON array (skills.json)
["owner/react-patterns", "./local/css-layout", "owner/ts-practices"]
JSON object with skills key
{
"name": "frontend-essentials",
"skills": ["owner/react-practices", "owner/ts-config"]
}
Plain text (skills.txt)
# comments use #
owner/react-patterns
./local/css-layout
owner/ts-practices
If the file has no extension, rolecraft tries .json and .txt variants automatically.
bundle create
Creates a JSON bundle file you can edit and share with your team:
rolecraft bundle create my-collection # creates my-collection.json
rolecraft bundle create # interactive: asks for name and path
Generated file:
{
"name": "my-collection",
"skills": [
"owner/skill-name"
]
}
Then edit the skills array and install with rolecraft bundle my-collection.json.
Options
| Flag | Description |
|---|---|
--dry-run |
Preview without installing |
--no-mcp |
Skip MCP server installation from skills |
Node.js API
This command is also available as a programmatic function. See the Node.js API documentation for detailed usage.
import { bundle } from 'rolecraft'
const result = await bundle(['./my-skill', 'owner/other-skill'])
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.
- 2d ago First seen · 87 lines · 0 tokens per session scan A 86bfca74fba2
bundle is a command published in the GitHub repository rolecraft-sh/rolecraft (75 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 463 tokens. 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 2026-08-30.
Other commands, from other repositories
pitchcraft.zh-CN
安装 pitchcraft skill（结构化说服与汇报）.
audit-artifacts
List suspicious root agent process files and placement directories.
rclone_convmv
Convert file and directory names in place.
init
Generate FILETREE.md from scratch. Confirms overwrite if it already exists. --self-only keeps every artifact out of git.
uninstall
Uninstall filetree from this repo — un-wires CLAUDE.md/AGENTS.md, removes generated artifacts (confirmed per item), tears down self-only mode if enabled.
audit
Diff live infrastructure against the spec and report drift by component name.