analyzing-cc-sessions

analyzing-cc-sessions is a skill for Claude Code, Codex from vladolaru/claude-code-plugins. It costs 71 tokens per session (4,459 once invoked), scanned A, original, MIT.

A guide and set of tools for reading Claude Code session logs, which record conversations and tool activity as JSONL files.

In plain words
What is it for?
Use it to parse session files, investigate failed subagents, correlate dispatches with their work, and calculate metrics such as tokens, duration, and tool calls.
Why use it?
It helps you reconstruct what an AI coding session or subagent actually did instead of relying on a summary. It can reveal errors, wasted work, and behavior patterns.

Skill for Claude CodeCodex

Part of the pirategoat-tools plugin — 22 skills shipped together

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.

agentmods
npx agentmods add skills/vladolaru/claude-code-plugins/analyzing-cc-sessions
Any agent
npx skills add vladolaru/claude-code-plugins --skill analyzing-cc-sessions
Clone the repo
git clone --depth 1 https://github.com/vladolaru/claude-code-plugins

Made for: Claude Code, Codex.

Or install pirategoat-tools, the plugin that ships this one along with the rest of its 22 skills.

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 analyzing-cc-sessions

README.md
[![agentmods](https://agentmods.dev/badge/skills/vladolaru/claude-code-plugins/analyzing-cc-sessions.svg)](https://agentmods.dev/skills/vladolaru/claude-code-plugins/analyzing-cc-sessions)
Your own site
<a href="https://agentmods.dev/skills/vladolaru/claude-code-plugins/analyzing-cc-sessions"><img src="https://agentmods.dev/badge/skills/vladolaru/claude-code-plugins/analyzing-cc-sessions.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,459 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.04459
Opus 5 $0.00036 $0.02230
Sonnet 5 $0.00014 $0.00892
Haiku 4.5 $0.00007 $0.00446

Measured yesterday against content hash 97e2e7851876, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyzing-cc-sessions 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 yesterday.

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.

plugins/pirategoat-tools/skills/analyzing-cc-sessions/SKILL.md · 439 lines

How it starts

The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Directory

Resolve SKILL_DIR to the absolute directory containing this SKILL.md, as shown by the current host, before using any bundled path below. Before a shell command uses $SKILL_DIR, assign it in that command or replace it with the resolved path. It is not a host-exported environment variable.

Analyzing Claude Code Raw Sessions

Overview

Claude Code stores every conversation as JSONL transcripts — one JSON object per line. Main sessions track the full human-agent dialogue. Subagent dispatches get their own JSONL files. Large tool outputs are persisted separately as text files.

Core principle: Main session = orchestration log. Subagent files = the real work. Tool-results = the large payloads. Most analysis targets subagent behavior, not the main session.

When to Use

  • Analyzing what happened in a CC session (efficiency, behavior, errors)
  • Parsing subagent logs for tool call patterns or waste
  • Extracting metrics (tokens, duration, tool counts, findings)
  • Debugging why a subagent failed or produced poor results
  • Building or maintaining session analysis scripts
  • Correlating main session dispatches with subagent execution

Before You Start

Your goal Start here
Understand what happened in a session Main session JSONL → find Agent tool calls → follow to subagent files
Analyze a specific subagent's behavior Subagent JSONL directly ({session}/subagents/agent-{id}.jsonl)
Extract metrics across sessions Existing analysis scripts (see below)
Debug why a subagent failed Subagent JSONL → last assistant entry → check for errors in preceding tool results
Correlate main session ↔ subagent Main session Agent tool_use → progress entries with agentId → subagent file

Session Data Locations

Project Directory

Sessions are stored per-project at:

~/.claude/projects/{path-hash}/

The {path-hash} is the absolute project path with / replaced by -, leading - stripped:

Read the full file on GitHub · 439 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. yesterday First seen · 439 lines · 71 tokens per session scan A 97e2e7851876

Subscribe to this mod's changes

analyzing-cc-sessions is a skill published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 4,459 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens