claude-session-dashboard: Skill for Claude Code

.claude/skills/analyze-skills/SKILL.md

analyze-skills is a skill for Claude Code from dlupiak/claude-session-dashboard. It costs 40 tokens per session (1,171 once invoked), scanned B, original, MIT.

A tool for analysing Claude Code session files to see which agent skills were injected and whether they were actually used.

In plain words
What is it for?
Use it to audit skill usage across subagent sessions and decide which skills to remove or keep.
Why use it?
It reveals unused instructions that consume context space and may make agent configurations less efficient.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

This is dlupiak/claude-session-dashboard's own configuration. It tells Claude Code how to work on claude-session-dashboard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-session-dashboard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dlupiak/claude-session-dashboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dlupiak/claude-session-dashboard/main/.claude/skills/analyze-skills/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dlupiak/claude-session-dashboard

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 analyze-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/dlupiak/claude-session-dashboard/analyze-skills/github.svg)](https://agentmods.dev/skills/dlupiak/claude-session-dashboard/analyze-skills)
Your own site
<a href="https://agentmods.dev/skills/dlupiak/claude-session-dashboard/analyze-skills"><img src="https://agentmods.dev/badge/skills/dlupiak/claude-session-dashboard/analyze-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.

agentmods 80×15 button for analyze-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/dlupiak/claude-session-dashboard/analyze-skills"><img src="https://agentmods.dev/badge/skills/dlupiak/claude-session-dashboard/analyze-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,171 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 23
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Agent Snooping · line 106
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00040 $0.01171
Opus 5 $0.00020 $0.00585
Sonnet 5 $0.00008 $0.00234
Haiku 4.5 $0.00004 $0.00117

Measured 9d ago against content hash 5d6af0f49d63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

analyze-skills scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find ~/.claude/projects/ -path "*/subagents/agent-*.jsonl" -type f 2>/dev/null
.claude/skills/analyze-skills/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Agent Skill Usage

You are analyzing Claude Code session files to determine which agent skills are actually used vs wasted context tokens.

What This Does

Scans ~/.claude/projects/ for subagent JSONL files, detects which skills were injected into each agent, and checks whether the agent actually referenced that skill's content. Produces a report with recommendations to optimize agent configurations.

Step 1: Find Subagent Files

Find all subagent JSONL files for the target project:

# If project argument provided, filter by it. Otherwise use current project.
# Subagent files live at: ~/.claude/projects/<encoded-path>/<session-id>/subagents/agent-*.jsonl
find ~/.claude/projects/ -path "*/subagents/agent-*.jsonl" -type f 2>/dev/null

If $ARGUMENTS.project is provided, filter paths containing that project name. If not provided, use the current working directory to determine the project.

Step 2: Read Agent Definitions

Read all agent files from .claude/agents/*.md in the current project. Extract:

  • Agent name (from frontmatter name:)
  • Skills list (from frontmatter skills:)

Step 3: Analyze Each Subagent File

For each subagent JSONL file:

3a. Identify the agent type

Look at the first user message — it usually contains the task description from the Task tool prompt. Cross-reference with the parent session if needed.

3b. Extract injected skills

Search the first 20 lines for <command-name>SKILL_NAME</command-name> markers. This tells you which skills were loaded into the agent's context.

3c. Check skill usage

For each injected skill, search the agent's assistant messages for distinctive keywords:

Skill Keywords to search for
uiux gray-950, terracotta, design system, bg-gray, border-gray
tanstack-start createServerFn, server function, TanStack Start, SSR
typescript-rules strict typing, Zod, z.object, z.infer, unknown, type guard
react-rules useQuery, useSuspenseQuery, queryOptions, named export, TanStack Query
testing vitest, describe, it, expect, vi.mock, happy-dom, testing-library
playwright-cli playwright, browser, e2e, spec.ts, page.goto
sdlc pipeline, SDLC, acceptance criteria

Read the full file on GitHub · 126 lines

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. 9d ago First seen · 126 lines · 40 tokens per session scan B 5d6af0f49d63

Subscribe to this mod's changes

analyze-skills is a skill published in the GitHub repository dlupiak/claude-session-dashboard (67 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,171 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Related

Other skills, from other repositories

claude-agent-sdk

Expert implementation guidance for the Claude Agent SDK (Python). Use when users are building with the Agent SDK — creating custom tools, managing sessions, controlling permissions, streaming responses, integrating MCP servers, adding hooks, defining subagents, or deploying SDK-based agents. Also use for SDK…

berekvolgyipeter/dotclaude · 107 tokens

ts-debug

TypeScript/Node debugging expert. Use when the user needs to debug, profile, or trace TypeScript or Node.js code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function", "why won't the process exit".

berekvolgyipeter/dotclaude · 68 tokens

py-debug

Python debugging expert. Use when the user needs to debug, profile, or trace Python code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function".

berekvolgyipeter/dotclaude · 54 tokens

agent-harness

Browse and explore agent harness frameworks and Claude Code resource collections. Use when the user wants to learn about, explore, or use agent orchestration frameworks, multi-agent architectures, or Claude Code resource catalogs — e.g., "how does Archon work?", "show me everything-claude-code resources", "find an…

berekvolgyipeter/dotclaude · 129 tokens

claude-code

Expert guidance on Claude Code configuration, capabilities, and troubleshooting. Use this skill whenever the user asks about Claude Code features, configuration, best practices, or troubleshooting — even if phrased informally. Covers MCP servers, plugins, skills, subagents, hooks, permissions, keybindings, settings…

berekvolgyipeter/dotclaude · 92 tokens

prompt-engineering

Expert prompt engineering guidance with proven techniques and anti-patterns. Invoke this skill whenever writing, editing, reviewing, or refining any prompt that will be interpreted by an AI model — system prompts, agent instructions, tool-use prompts, command templates, multi-step task prompts, or agentic workflows.…

berekvolgyipeter/dotclaude · 127 tokens