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/commands/athola/claude-night-market/improve-skills)<a href="https://agentmods.dev/commands/athola/claude-night-market/improve-skills"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/improve-skills/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/commands/athola/claude-night-market/improve-skills"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/improve-skills.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 | $0.00017 | $0.01672 |
| Opus 5 | $0.00009 | $0.00836 |
| Sonnet 5 | $0.00003 | $0.00334 |
| Haiku 4.5 | $0.00002 | $0.00167 |
Grade A, and why
improve-skills 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 12d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Skills from Observability Data
Automatically identify and implement skill improvements based on execution logs and user evaluations.
Usage
/abstract:improve-skills # Analyze all skills
/abstract:improve-skills --skill proof-of-work # Improve specific skill
/abstract:improve-skills --top 5 # Top 5 improvement opportunities
/abstract:improve-skills --dry-run # Preview without implementing
Purpose
Part of Issue #69 Phase 5, this command closes the self-improvement loop by:
- Reading LEARNINGS.md for improvement opportunities
- Prioritizing by severity (frequency × impact × ease)
- Generating skill update proposals
- Optionally implementing changes with validation
What It Does
- Loads LEARNINGS.md from
~/.claude/skills/LEARNINGS.md - Identifies opportunities:
- High-impact issues (failure rates, excessive failures)
- Slow execution times
- Low user ratings with specific friction points
- Prioritizes improvements:
- Frequency: How often is this skill used?
- Impact: How much does the issue hurt?
- Ease: How simple is the fix?
- Generates proposals:
- What to change (specific file/section)
- Why (data from evaluations)
- How (implementation approach)
- Optionally implements:
- Updates skill files
- Runs validation tests
- Creates commit
Prioritization Formula
Priority Score = (Frequency × Impact) / Ease
Where:
- Frequency: Execution count in analysis period
- Impact:
- High failure rate: 10
- Low rating: rating_diff × 2 (e.g., 2.5 vs 5.0 = 5.0 impact)
- Slow execution: seconds_over_threshold / 10
- Ease:
- Simple text update: 1
- Add examples: 2
- Restructure workflow: 5
- Refactor logic: 10
Threshold: Priority > 5.0 = implement now, 2.0-5.0 = discuss, <2.0 = defer
Examples
Analyze All Skills
/abstract:improve-skills
# Output:
# Reading LEARNINGS.md...
# Found 12 improvement opportunities
#
# Top 5 by priority:
# 1. imbue:proof-of-work (Priority: 8.5)
# Issue: 42% failure rate (11/26 executions)
# Fix: Add error handling for missing PROOF.md
# Ease: Simple (add try/catch)
#
# 2. abstract:skill-auditor (Priority: 6.2)
# Issue: 2.8/5.0 rating - "too verbose"
# Fix: Add --quiet flag
# Ease: Medium (new parameter)
# ...
#
# Implement top 5? (y/n):
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.
- 12d ago First seen · 248 lines · 17 tokens per session scan A 7d604bb0a441
improve-skills is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,672 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
analyze-codebase
Generate comprehensive analysis and documentation of entire codebase.
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.
ui-copywriter
Use when writing marketing or landing copy. Headlines, hero copy, CTAs, value propositions and section copy that sound like a person making a specific claim rather than a template being filled in.
data-visualization-specialist
Use when a chart misleads or confuses. Wrong chart type for the data, a truncated axis, colour that encodes nothing, unreadable labels on mobile, or charts no screen reader can use.