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/agents-xmlgit 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 | $0.00389 |
| Opus 5 | $0.00000 | $0.00195 |
| Sonnet 5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
agents-xml 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.
What it actually says
rolecraft agents-xml
Generate a <skills_system> XML block listing installed skills, compatible with Claude Code and other spec-compliant AI agents.
Usage
# Output XML to stdout
rolecraft agents-xml
# Write/replace the XML section in AGENTS.md
rolecraft agents-xml --write
Description
Reads the global and project lockfiles, finds each installed skill's SKILL.md, extracts its name and description from YAML frontmatter, and generates a <skills_system> XML block that AI agents can parse to discover available skills.
When --write is passed, it writes or replaces the <skills_system> section in ./AGENTS.md. Other content in the file is preserved.
Example output
$ rolecraft agents-xml
<skills_system>
Only use skills listed in <available_skills> below.
Do not invoke a skill that is already loaded in your context.
<available_skills>
<skill>
<name>task-decomposer</name>
<description>Breaks complex tasks into manageable subtasks</description>
<location>global</location>
</skill>
<skill>
<name>code-review</name>
<description>Automated code review best practices</description>
<location>project</location>
</skill>
</available_skills>
</skills_system>
Integration with Claude Code
Once the XML is written to AGENTS.md, Claude Code and other spec-compliant agents automatically discover the skills and make them available via their native skill-loading mechanism.
Node.js API
This command is also available as a programmatic function. See the Node.js API documentation for detailed usage.
import { agentsXml } from 'rolecraft'
const { xml } = await agentsXml()
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.
- 3d ago First seen · 57 lines · 0 tokens per session scan A 5f44c33353b5
agents-xml is a command published in the GitHub repository rolecraft-sh/rolecraft (75 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 389 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
optimize
Optimize performance [target].
plan-infra
Confirm requirements with the user first, then design cloud infrastructure and write a reproducible spec + diagram into the repo.
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.
rclone_copy
Copy files from source to dest, skipping identical files.
rclone_listremotes
List all the remotes in the config file and defined in environment variables.