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/ncssm-robotics/ftc-claude/validate-skillgit clone --depth 1 https://github.com/ncssm-robotics/ftc-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ncssm-robotics/ftc-claude/validate-skill)<a href="https://agentmods.dev/commands/ncssm-robotics/ftc-claude/validate-skill"><img src="https://agentmods.dev/badge/commands/ncssm-robotics/ftc-claude/validate-skill.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00008 | $0.00855 |
| Opus 5 | $0.00004 | $0.00428 |
| Sonnet 5 | $0.00002 | $0.00171 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
validate-skill 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Skill Command
Validates that an FTC skill plugin follows marketplace requirements and best practices.
Usage
/validate-skill <skill-name>
Arguments:
skill-name: Name of the skill to validate (must exist inplugins/)
Examples
/validate-skill pedro-pathing
/validate-skill rev-hub
Validation Checks
Structure Checks
-
plugins/<skill-name>/directory exists -
plugins/<skill-name>/plugin.jsonexists and is valid JSON -
plugins/<skill-name>/skills/<skill-name>/directory exists -
plugins/<skill-name>/skills/<skill-name>/SKILL.mdexists
plugin.json Checks
- Has
namefield matching directory name - Has
descriptionfield (non-empty) - Has
versionfield (semver format) - Has
licensefield - Has
tagsarray with "ftc" - Has
compatibility.agentsarray
SKILL.md Frontmatter Checks
- Has YAML frontmatter (starts with
---) - Has
namefield matching directory name - Has
descriptionfield (non-empty, < 1024 chars) -
descriptionincludes WHAT the skill does -
descriptionincludes WHEN to use it (trigger words) - Has
licensefield - Has
metadata.categoryfield - Has
metadata.versionfield
Content Quality Checks
- SKILL.md is under 500 lines
- Has "Quick Start" or "## Quick" section
- Has code examples (
java orkotlin blocks) - Has "Anti-Pattern" or "Don't" section
- No
[TODO: ...]placeholders remaining - No hardcoded file paths from template
marketplace.json Check
- Skill is listed in
.claude-plugin/marketplace.json - Entry has correct
pathfield
Script Checks (if scripts/ exists)
- All
.shfiles are executable - All
.pyfiles are executable - Scripts have shebang line
Output Format
Report results as:
Validating skill: <skill-name>
Structure:
✓ plugin.json exists
✓ SKILL.md exists
✗ Missing scripts/ directory (optional)
plugin.json:
✓ Valid JSON
✓ Name matches directory
✗ Missing 'ftc' in tags
SKILL.md:
✓ Valid frontmatter
✓ Description includes WHAT
✗ Description missing WHEN triggers
✓ Under 500 lines (127 lines)
Content:
✓ Has Quick Start section
✓ Has code examples
✗ Missing Anti-Patterns section
✗ Contains [TODO: ...] placeholders
marketplace.json:
✓ Skill is registered
Summary: 8/12 checks passed
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.
- 5d ago First seen · 138 lines · 8 tokens per session scan A a22b770b7a7c
validate-skill is a command published in the GitHub repository ncssm-robotics/ftc-claude (4 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 855 once invoked, about $0.0000 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.
Other commands, from other repositories
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.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.