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.
git clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/agents/athola/claude-night-market/skill-evaluator)<a href="https://agentmods.dev/agents/athola/claude-night-market/skill-evaluator"><img src="https://agentmods.dev/badge/agents/athola/claude-night-market/skill-evaluator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/athola/claude-night-market/skill-evaluator"><img src="https://agentmods.dev/badge/agents/athola/claude-night-market/skill-evaluator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.01966 |
| Opus 5.5 | $0.00011 | $0.00786 |
| Sonnet 5.5 | $0.00005 | $0.00393 |
| Haiku 4.5 | $0.00003 | $0.00197 |
Grade A, and why
skill-evaluator 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Execution Evaluator
Facilitates human-in-loop qualitative evaluation of skill executions.
Purpose
Part of the skill observability infrastructure (Issue #69 Phase 2), this agent helps capture qualitative feedback about skill effectiveness that cannot be detected programmatically.
Inputs
- skill_name: Skill to evaluate (format:
plugin:skill-name) - mode:
recent(default),all, ordate - date: Specific date to evaluate (YYYY-MM-DD format)
- batch: Boolean - evaluate multiple executions interactively
Workflow
1. Load Execution Logs
# Read from ~/.claude/skills/logs/<plugin>/<skill>/
# Parse JSONL files
# Filter for unevaluated entries (qualitative_evaluation == null)
2. Present Execution Summary
For each unevaluated execution, show:
- Timestamp (human-readable)
- Duration (ms → seconds conversion)
- Outcome (success/failure/partial)
- Context preview (first 200 chars of output)
- Session information
3. Collect Evaluation
Prompt user with structured questions:
Q1: Effectiveness Rating (1-5)
How effective was this skill execution?
5 - Exceptional (exceeded expectations)
4 - Effective (achieved goal with minor friction)
3 - Adequate (worked but had inefficiencies)
2 - Poor (partial failure or workarounds needed)
1 - Failed (did not achieve intended outcome)
Rating: _
Q2: Friction Points (optional, multi-line)
What friction did you encounter? (Press Enter twice to finish)
Examples:
- Missing information about X
- Unclear instructions for Y
- Excessive token usage
- Outdated guidance
Friction: _
Q3: Improvement Suggestions (optional, multi-line)
What would make this skill better? (Press Enter twice to finish)
Examples:
- Add examples for X
- Simplify language in section Y
- Split into smaller skills
- Add error recovery steps
Suggestions: _
Q4: Additional Notes (optional, single line)
Any other observations?
Notes: _
4. Update Log Entry
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 Changed · +24 tokens per session 7c6f41421d72
- 2mo ago First seen · 332 lines · 3 tokens per session scan A e6b0b92b3ea2
skill-evaluator is an agent published in the GitHub repository athola/claude-night-market (343 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,966 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
database
Database schema, Eloquent models, and migrations.
ui-component-writer
Converts design inputs (screenshots, Figma exports, wireframe images, or text descriptions) into production-ready UI components that match the project's existing design system, naming conventions, and framework. Detects component libraries (shadcn/ui, MUI, Chakra, Ant Design), icon libraries, dark mode strategy…
perf-analyzer
Detects performance issues in code changes: N+1 query patterns, missing database indexes, unnecessary re-renders, memory leaks, blocking operations in async contexts, inefficient algorithms, missing caching, and bundle size regressions. Use on backend, frontend, and data processing code changes.
documentation-analyst-writer
Synthesizes outputs from multiple RPI research agents into structured artifact files — RESEARCH.md, pm.md, ux.md, eng.md, and PLAN.md. Also writes implementation records (IMPLEMENT.md). Called by RPI orchestrating commands.
agent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.