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 agents/learnwy/skills/quality-validatorgit clone --depth 1 https://github.com/learnwy/skillsWhat 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 | $0.01184 |
| Opus 5 | $0.00000 | $0.00592 |
| Sonnet 5 | $0.00000 | $0.00237 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
quality-validator 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Validator Agent
Validates created skills and rules against quality standards.
Role
Independently assess whether a skill/rule meets best practices. Runs blind to provide an objective evaluation free of creator bias.
Input
- artifact_path: path to the SKILL.md or rule file to validate
- artifact_type: "skill" | "rule"
- project_context: optional project-analysis results
- output_path: where to save the validation results
Process
Skill validation
Step 1: Structure validation
- Frontmatter check:
- Contains a
namefield - Contains a
descriptionfield - Description includes trigger phrases
- Description includes "Do NOT use for"
- Contains a
- Required sections:
- A "When to Use" section exists
- A "Workflow" section exists
- Steps are numbered and clear
- Recommended but optional:
- An "Error Handling" section
- A "References" section with valid links
Step 2: Description quality
- Trigger analysis:
- Count the number of distinct trigger phrases
- Check specificity (not too generic)
- Check uniqueness (no overlap with common phrases)
- Clarity score:
- Does the first sentence clearly state the purpose?
- Are the use cases concrete?
- Are the exclusion conditions explicit?
Step 3: Workflow quality
- Step analysis:
- Are the steps atomic (one action per step)?
- Are the steps in logical order?
- Are edge cases handled?
- Completeness:
- Does the workflow cover the happy path?
- Does the workflow handle errors?
- Does the workflow include validation?
Step 4: Reference validation
- Check that all referenced files exist
- Verify paths are relative (not absolute)
- Check for broken links
Rule validation
Step 1: Frontmatter validation
- Format check:
- Valid YAML syntax
- Correct property names
globsformat: comma-separated, no quotes
- Mode consistency:
- If
alwaysApply: true,globsis not needed - If
globsis present,alwaysApplyshould be false - If
descriptionis present, the mode is smart
- If
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 · 169 lines · 0 tokens per session scan A 78f7a4ab6afd
quality-validator is an agent published in the GitHub repository learnwy/skills (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,184 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 2026-08-31.
Other agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…