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/testgit 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 | $0.01042 |
| Opus 5 | $0.00000 | $0.00521 |
| Sonnet 5 | $0.00000 | $0.00208 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade B, and why
test scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `dangerous-patterns` | 15 | No `rm -rf`, `eval`, `exec`, `sudo`, `/etc/passwd` patterns | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rolecraft test
Test a SKILL.md quality with built-in assertions. Scans frontmatter, content structure, security patterns, and completeness — then assigns a score and grade.
Usage
rolecraft test <skill-path> # Test a single skill
rolecraft test --all # Test all installed skills
rolecraft test --all --json # JSON output for CI
Options
| Flag | Description |
|---|---|
--all |
Test all installed skills from lockfile |
--json |
Machine-readable JSON output |
--verbose, -v |
Detailed assertion results |
--min-score <N> |
Fail if score below N (default: 50) |
--only <names> |
Run specific assertions only (comma-separated) |
--no-color |
Disable ANSI colors |
--no-emoji |
Replace emojis with ASCII ([OK], [FAIL], [WARN]) |
Assertions
| Assertion | Weight | Description |
|---|---|---|
name-defined |
10 | frontmatter.name must exist |
description-defined |
10 | frontmatter.description must exist |
description-length |
5 | Description >= 20 characters |
frontmatter-valid |
10 | YAML delimiters (---) must be present and parseable |
slug-defined |
5 | frontmatter.slug must exist |
content-not-empty |
10 | Body must contain >= 50 words |
code-block-lang |
10 | Code fences must have language tags (```js not ```) |
dangerous-patterns |
15 | No rm -rf, eval, exec, sudo, /etc/passwd patterns |
line-length |
5 | No lines exceeding 120 characters |
example-commands |
10 | Must contain $ command or ```bash block |
mcp-referenced |
5 | If MCP servers referenced in body, they must be in frontmatter |
agent-targets |
5 | Must specify agents: or scope: in frontmatter |
has-sections |
5 | Must have at least 2 ## sections |
Grades
| Score | Grade | Meaning |
|---|---|---|
| 90-100 | A | Excellent |
| 75-89 | B | Good |
| 50-74 | C | Adequate |
| 25-49 | D | Poor |
| 0-24 | F | Unusable |
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 · 118 lines · 0 tokens per session scan B dbd260cccdde
test 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 1,042 tokens. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
harness-parallel
Run the parallel Auto-Harness orchestration flow with worktree workers. /auto-harness:harness-parallel.
harness
Run the full Auto-Harness orchestration flow. /auto-harness:harness.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.