conversation-analyzer

conversation-analyzer is a skill for Claude Code from mhattingpete/claude-skills-marketplace. It costs 48 tokens per session (877 once invoked), scanned A, original, Apache-2.0.

A tool that examines Claude Code conversation history for recurring work patterns, mistakes, and opportunities to improve how coding tasks are handled. Claude Code is a programming assistant that works through chat and a code workspace.

In plain words
What is it for?
Use it to review request types, active projects, working times, recurring errors, vague requests, and tasks that could be automated.
Why use it?
It reveals repeated problems or tasks that may otherwise be hard to notice across many conversations.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the productivity-skills-plugin plugin — 4 skills shipped together

Good fit Use it to review request types, active projects, working times, recurring errors, vague requests, and tasks that could be automated.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mhattingpete/claude-skills-marketplace/conversation-analyzer
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 mhattingpete/claude-skills-marketplace --skill conversation-analyzer
Clone the repo
git clone --depth 1 https://github.com/mhattingpete/claude-skills-marketplace

Made for: Claude Code.

Or install productivity-skills-plugin, the plugin that ships this one along with the rest of its 4 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 conversation-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/mhattingpete/claude-skills-marketplace/conversation-analyzer/github.svg)](https://agentmods.dev/skills/mhattingpete/claude-skills-marketplace/conversation-analyzer)
Your own site
<a href="https://agentmods.dev/skills/mhattingpete/claude-skills-marketplace/conversation-analyzer"><img src="https://agentmods.dev/badge/skills/mhattingpete/claude-skills-marketplace/conversation-analyzer/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 conversation-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/mhattingpete/claude-skills-marketplace/conversation-analyzer"><img src="https://agentmods.dev/badge/skills/mhattingpete/claude-skills-marketplace/conversation-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 877 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

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 →

  • medium Rogue Agent · line 67
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00048 $0.00877
Opus 5 $0.00024 $0.00439
Sonnet 5 $0.00010 $0.00175
Haiku 4.5 $0.00005 $0.00088

Measured 13d ago against content hash fd3d2843c619, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

conversation-analyzer 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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze_history.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

productivity-skills-plugin/skills/conversation-analyzer/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Analyzer

Analyzes your Claude Code conversation history to identify patterns, common mistakes, and workflow improvement opportunities.

When to Use

  • "analyze my conversations"
  • "review my Claude Code history"
  • "what patterns do you see in my usage"
  • "how can I improve my workflow"
  • "am I using Claude Code effectively"

What It Analyzes

  1. Request type distribution (bug fixes, features, refactoring, queries, testing)
  2. Most active projects
  3. Common error keywords
  4. Time-of-day patterns
  5. Repetitive tasks (automation opportunities)
  6. Vague requests causing back-and-forth
  7. Complex tasks attempted without planning
  8. Recurring bugs/errors

Analysis Scope

Default: Last 200 conversations for recency and relevance.

Methodology

1. Request Type Distribution

Categorizes by: bug fixes, feature additions, refactoring, information queries, testing, other.

2. Project Activity

Tracks which projects consume most time, identifies project-specific patterns.

3. Time Patterns

Hour-of-day usage distribution, identifies peak productivity times.

4. Common Mistakes

  • Vague requests: Initial requests lacking context vs. acceptable follow-ups
  • Repeated fixes: Same issues occurring multiple times
  • Complex tasks: Multi-step requests without planning
  • Repetitive commands: Manual tasks that could be automated

5. Error Analysis

Frequency of error-related requests, common error keywords, recurring problems.

6. Automation Opportunities

Identifies repeated exact requests, suggests skills, slash commands, or scripts.

Output

Structured report with:

  • Statistics: Request types, active projects, timing patterns
  • Patterns: Common tasks, repetitive commands, complexity indicators
  • Issues: Specific problems with examples
  • Recommendations: Prioritized, actionable improvements

Tools Used

  • Read: Load history file (~/.claude/history.jsonl)
  • Write: Create analysis reports if requested
  • Bash: Execute Python analysis script
  • Direct analysis: Parse JSON programmatically

Read the full file on GitHub · 130 lines

Files

What ships with it

1 file 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. 13d ago First seen · 130 lines · 48 tokens per session scan A fd3d2843c619

Subscribe to this mod's changes

conversation-analyzer is a skill published in the GitHub repository mhattingpete/claude-skills-marketplace (671 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 877 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens

stride-analysis-patterns

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

sangrokjung/claude-forge · 30 tokens

review-loop

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…

sangrokjung/claude-forge · 100 tokens

prompts-chat

Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.

sangrokjung/claude-forge · 41 tokens

humanize-korean

A Korean editing tool that removes translation-like phrasing and common AI writing habits while preserving facts, numbers, names, and quotations. It is intended for existing Korean prose, not for writing new marketing copy.

sangrokjung/claude-forge · 145 tokens

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

sangrokjung/claude-forge · 33 tokens