agentmods.dev

improve-session

A session-analysis tool for Claude Code, an AI coding assistant. It examines a coding session and reports repeated work, failed tools, large file reads, and linter-related edit cycles.

In plain words
What is it for?
Use it to review a recent, current, or saved Claude Code session and get suggestions for improving the workflow.
Why use it?
It helps identify wasted tokens, repeated tasks, and patterns that make coding sessions longer or less reliable.

Skill for Claude CodeCodex

2 8d ago B scan 52 tokens original MIT
View the source file ericboehs/claude-plugins
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/ericboehs/claude-plugins/improve-session
Any agent
npx skills add ericboehs/claude-plugins --skill improve-session
Clone the repo
git clone --depth 1 https://github.com/ericboehs/claude-plugins

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00052 $0.01061
Opus 5 $0.00026 $0.00531
Sonnet 5 $0.00010 $0.00212
Haiku 4.5 $0.00005 $0.00106

Measured yesterday against content hash 21dd010286e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

improve-session 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/parse-session.rb), 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.

Reads agent configuration directoriesmediumAgent snooping

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

- The global `~/.claude/settings.json`
plugins/session-improver/skills/improve-session/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Improver

Analyze Claude Code session transcripts and generate actionable recommendations to reduce token waste, prevent linter loops, and automate repetitive workflows.

Usage

  • /improve-session — Analyze the most recent session
  • /improve-session <session-id> — Analyze a specific past session
  • /improve-session --current — Analyze the current live session

Workflow

Phase 1: Parse the session

Run the parser script to extract a structured summary:

ruby "${CLAUDE_SKILL_DIR}/scripts/parse-session.rb" <session-id-or-path>

If CLAUDE_SKILL_DIR is not set, fall back to the skill's location relative to this file. You can detect it by looking at the directory containing this SKILL.md.

The argument is either:

  • A session UUID (found in ~/.claude/history.jsonl)
  • --current for the most recent session
  • A direct path to a .jsonl file

The script outputs JSON with these sections:

  • linter_loops — Linter smells that triggered multiple edit cycles
  • tool_failures — Tools that failed and were retried
  • repeated_sequences — Workflow patterns that repeated 3+ times
  • large_reads — Files read 3+ times in the session
  • hook_failures — Hooks that failed repeatedly
  • permission_events — Tools that needed human approval

Phase 2: Read context

For each finding, read relevant project files to understand what's already configured:

  • The project's CLAUDE.md (if the session had a project path)
  • The project's .claude/settings.json and .claude/settings.local.json
  • The project's .claude/hooks/ directory
  • Any .reek.yml, .rubocop.yml, eslint.config.*, etc.
  • The global ~/.claude/CLAUDE.md
  • The global ~/.claude/settings.json

Phase 3: Generate recommendations

Read the reference files for patterns and templates (relative to this SKILL.md):

  • references/analyzers.md — What each finding type means
  • references/fix-templates.md — Templates for each fix type
  • references/ruby-linter-patterns.md — Ruby-specific patterns

Read the full file on GitHub · 112 lines

Files

What ships with it

4 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. yesterday First seen · 112 lines · 52 tokens per session scan B 21dd010286e3

Subscribe to this mod's changes

improve-session is a skill published in the GitHub repository ericboehs/claude-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 1,061 once invoked, about $0.0003 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 2026-08-31.

Code reviewProductivity
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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens