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/composegit 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 | $0.00795 |
| Opus 5 | $0.00000 | $0.00398 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
compose 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rolecraft compose
Combine multiple SKILL.md files into a single composed skill. Supports two composition strategies: merge (deduplicate) and chain (override).
Usage
rolecraft compose <a> <b> [<c> ...] # Merge mode (default), output to stdout
rolecraft compose <a> <b> -o combined.SKILL.md # Write to file
rolecraft compose <a> <b> --chain --name combined # Chain mode with custom name
Options
| Flag | Description |
|---|---|
-o, --output <path> |
Output file path (default: stdout) |
--chain |
Chain mode — later skills override same sections |
--name <name> |
Custom name for the composed skill |
--dry-run |
Preview compose result without writing |
--force |
Overwrite existing output file |
--json |
JSON output with stats |
--no-color |
Disable ANSI colors |
Modes
Merge (default)
Combines all sections, deduplicating same-named sections line-by-line. Lines that already exist in the first skill are not duplicated.
Section "Code Style" from skill A + skill B:
Use 2-space indentation ← from A (kept)
Use single quotes ← from A (kept)
Write tests first ← from B (unique, added)
Chain
Sequences skills with override — later skills overwrite same-named sections entirely. Useful for team-specific overrides:
Base skill → Team A overrides → Team B customizations
How it works
- Parse each SKILL.md (frontmatter + section list)
- In merge mode: collect all sections, merge same-named ones (set-based dedup)
- In chain mode: iterate sections in order, later wins for same heading
- Merge frontmatter from all sources (first name wins, first slug wins, rest accumulate)
- Generate auto-description from source names if not provided
- Output composed SKILL.md
Examples
$ rolecraft compose ./react.SKILL.md ./testing.SKILL.md -o ./react-testing.SKILL.md
✓ Written to ./react-testing.SKILL.md
Composing 2 skills (merge mode)...
Compose result:
✓ 3 sections composed
✓ 4 frontmatter fields
✓ Sources: 2
✓ Mode: merge
✓ Input: 4 sections → Output: 3 sections
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 · 106 lines · 0 tokens per session scan A aa509666581a
compose 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 795 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.
takeoff
항공기 이륙 4단계 — develop 리베이스 → push → PR 생성 (원격 영향).
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.