skill-monitor

skill-monitor is a skill for Claude Code from slbug/claude-ruby-grape-rails. It costs 28 tokens per session (794 once invoked), scanned A, original, MIT.

An exploratory dashboard for reviewing how well skills performed across scanned coding sessions. It reads recorded session measurements and offers optional recommendations for improvement.

In plain words
What is it for?
Use it to review all skills, inspect one skill, filter by time period or provider, or request follow-up improvement analysis after a session scan.
Why use it?
It helps identify possible patterns in skill use without treating those observations as proof that a skill works or fails.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to review all skills, inspect one skill, filter by time period or provider, or request follow-up improvement analysis after a session scan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/slbug/claude-ruby-grape-rails/skill-monitor
Install

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.

Any agent
npx skills add slbug/claude-ruby-grape-rails --skill skill-monitor
Clone the repo
git clone --depth 1 https://github.com/slbug/claude-ruby-grape-rails

Made for: Claude Code.

Wrote 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.

agentmods badge for skill-monitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/skill-monitor/github.svg)](https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/skill-monitor)
Your own site
<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/skill-monitor"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/skill-monitor/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.

agentmods 80×15 button for skill-monitor

Your own site · 80×15
<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/skill-monitor"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/skill-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00794
Opus 5 $0.00014 $0.00397
Sonnet 5 $0.00006 $0.00159
Haiku 4.5 $0.00003 $0.00079

Measured 11d ago against content hash 9dcc48b191bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-monitor 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 11d 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.

.claude/skills/skill-monitor/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Monitor

Audience: Agents, Not Humans

Imperative-only. Exploratory — does NOT prove a skill is good or bad on its own.

Requirements

.claude/session-metrics/metrics.jsonl (from /session-scan).

Trust Order

Before trusting the dashboard:

  1. claude plugin validate --strict plugins/ruby-grape-rails
  2. make eval or make eval-all
  3. /docs-check if Claude docs drift suspected
  4. /skill-monitor — corroborating observational input

Usage

Command Behavior
/skill-monitor dashboard for all skills
/skill-monitor --skill review scoped to one skill
/skill-monitor --improve delegates to skill-effectiveness-analyzer
/skill-monitor --window 30d broader window
/skill-monitor --provider claude-code exact provider

Workflow

1. Parse Arguments

Flag Values
--skill NAME
--improve (no value, triggers analyzer mode)
--window 7d / 30d / all
--provider NAME

2. Load Metrics

Read .claude/session-metrics/metrics.jsonl. Extract skill_effectiveness.

No skill_effectiveness data → tell contributor to rescan with current scorer.

--provider present → restrict dashboard to that provider.

3. Compute Observational Aggregates

Useful aggregates:

  • total invocations
  • sessions used in
  • weighted action rate
  • weighted avg post-errors
  • weighted avg post-corrections
  • dominant outcomes

Baseline comparison computed → present as heuristic context, NOT causal effect estimate.

4. Display the Dashboard

Show:

  • window + provider scope
  • sample sizes
  • per-skill aggregates
  • low-confidence warnings for thin samples

Flagged skills are review candidates, NOT proven regressions.

5. Improvement Mode

--improve requested → delegate to skill-effectiveness-analyzer.

Analyzer requirements:

  • use the improvement template
  • cite session evidence
  • list confounders
  • look for corroboration in lab/eval, docs-check, previous session-analysis reports

Read the full file on GitHub · 122 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 11d ago First seen · 122 lines · 28 tokens per session scan A 9dcc48b191bf

Subscribe to this mod's changes

skill-monitor is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 6d ago), licensed MIT. It adds 28 tokens to every session and 794 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 2026-08-31.