mining-session-patterns

A tool for examining Claude Code session transcripts, which are saved conversation logs in JSONL files. It looks for repeated patterns such as errors followed by fixes and tool failures.

In plain words
What is it for?
Use it to scan recent Claude Code sessions and write findings to a patterns document. You can choose a time period and an output file.
Why use it?
It turns many raw session logs into a shorter record of what tends to go wrong and what fixes work. This helps identify recurring problems and track how much work or cost different tasks require.

Skill for Claude CodeCodex

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/qte77/claude-code-plugins/mining-session-patterns
Any agent
npx skills add qte77/claude-code-plugins --skill mining-session-patterns
Clone the repo
git clone --depth 1 https://github.com/qte77/claude-code-plugins

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 957 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 $0.00037 $0.00957
Opus 5 $0.00018 $0.00478
Sonnet 5 $0.00007 $0.00191
Haiku 4.5 $0.00004 $0.00096

Measured yesterday against content hash 374514a6300b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mining-session-patterns 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/cc-meta/skills/mining-session-patterns/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Pattern Mining

Target: $ARGUMENTS

Mines Claude Code session transcripts for recurring patterns that feed compound learning. Converts raw session data into actionable improvements.

Arguments

Position Name Required Default Description
1 time-range no 7d Period to scan. E.g. 7d, 30d, this-week.
2 output-path no docs/patterns/session-patterns.md Where to write findings.

Examples:

/mining-session-patterns                    # Last 7 days, default output
/mining-session-patterns 30d                # Last 30 days
/mining-session-patterns 7d ./patterns.md   # Custom output path

Data Source

~/.claude/projects/*/*.jsonl    # Session transcripts

Critical: Never bulk-read full .jsonl files. Use sampling strategy below to respect context budget.

Workflow

  1. Discover session files — Glob ~/.claude/projects/*/*.jsonl. Filter by mtime within time-range. Select up to 10 files, preferring recent.

  2. Sample each file — Read first 20 lines + last 20 lines per file. This captures session setup (tools, config) and final outcomes (errors, completions). Skip files smaller than 5 lines.

  3. Extract patterns from sampled lines:

    • Error-fix sequences: Tool call with error response followed by a successful retry or different approach. Look for type: "tool_error" or error messages in tool results, then the next tool call on the same target.
    • Tool failure rates: Count tool calls and failures per tool type (Bash, Edit, Read, Grep, Glob, Write). A failure is any tool result containing error indicators.
    • Cost signals: Estimate token usage per session from message counts and approximate message sizes. Map to task complexity (small/medium/large) based on message count thresholds: <20 small, 20-80 medium, >80 large.
  4. Format findings — Structure as tables per Output Format below. Every row must suggest a concrete improvement or be omitted.

Read the full file on GitHub · 109 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 · 109 lines · 0 tokens per session scan A 374514a6300b

Subscribe to this mod's changes

mining-session-patterns is a skill published in the GitHub repository qte77/claude-code-plugins (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 957 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 2026-08-31.

Related

Other skills, from other repositories

orchestrator

FULLY AUTONOMOUS Flutter development pipeline orchestrator. Smart routing: PM analyzes -> creates targeted tasks -> Orchestrator executes only needed agents. Supports Asana task URLs. Includes QE verification via Maestro E2E tests. 7-phase flow: PM -> TodoWrite -> Execute -> Review -> Tests -> QE E2E -> Close.

aleksandr-chaika/flutter-clean-arch-skills · 72 tokens

flutter-guide

Flutter/BLoC Clean Architecture patterns, review checklists, and testing guides. Background knowledge for flutter-dev, flutter-reviewer, flutter-tester. Not user-invocable.

aleksandr-chaika/flutter-clean-arch-skills · 39 tokens

maestro-flutter

Maestro E2E testing knowledge for Flutter apps. YAML-based flows, TestKeys, visual regression, Maestro MCP integration. Background knowledge for QE E2E testing phase.

aleksandr-chaika/flutter-clean-arch-skills · 41 tokens

android-kotlin-compose

Android development with Kotlin and Jetpack Compose. Use when user mentions "Compose", "Jetpack Compose", "Material3", "Hilt", "Room", "ViewModel", or needs to build Android UI, implement MVVM architecture, manage Compose state, or integrate Jetpack libraries (Navigation, Room, Hilt, ViewModel). Triggers on…

and3r817/dot-claude-plugins · 84 tokens

android-kotlin-coroutines

Android development with Kotlin Coroutines and Flow. Use when user mentions "coroutines", "suspend", "Flow", "StateFlow", "SharedFlow", "viewModelScope", "lifecycleScope", or needs to implement async programming, handle structured concurrency, integrate coroutines with Retrofit/Room/WorkManager, or write coroutine…

and3r817/dot-claude-plugins · 87 tokens

codex-advisor

Advisory consultation skill for architectural reviews, design decisions, code analysis, and technology evaluation. Codex provides recommendations without making code changes. Invoked by phrases like "consult Codex", "get Codex's opinion", "ask Codex about", "have Codex review", "Codex analysis", "validate this…

and3r817/dot-claude-plugins · 85 tokens