Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Session Compare

ASecurity

Compare two Claude Code sessions by path or name. Extracts duration, model, all token buckets, estimated cost, human turns, tool calls, files touched, and generates a markdown conversation summary. CLI wrapper around ~/dotfiles/stapler-scripts/session-compare.

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsswiftbash

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill session-compare --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Session Compare?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Session Compare
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-session-compare/badge)](https://www.skillsdirectory.com/skills/tstapler-session-compare)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: session-compare
description: Compare two Claude Code sessions by path or name. Extracts duration, model, all token buckets, estimated cost, human turns, tool calls, files touched, and generates a markdown conversation summary. CLI wrapper around ~/dotfiles/stapler-scripts/session-compare.
---

# Session Comparison

Compare two Claude Code sessions and produce a structured markdown report.

## When to use

- Evaluating different approaches (quick vs MDD, two prompt strategies, two models)
- Estimating cost difference between workflows
- Creating demo artifacts that show session metrics side-by-side
- Post-session retrospectives: "what did each approach actually cost?"

## How it works

The `session-compare` CLI parses `.jsonl` transcripts stored under `~/.claude/projects/` and outputs:

- Side-by-side metric table (duration, model, all 4 token buckets, cost)
- Per-session cost breakdown table
- Files touched (union, with per-session checkmarks)
- Full conversation summaries (user + assistant text, tool call annotations) — human-readable markdown, not raw JSONL

## Invocation

```bash
# By full .jsonl path
session-compare /path/to/session1.jsonl /path/to/session2.jsonl

# By project directory (picks newest .jsonl)
session-compare ~/.claude/projects/-Users-me-project-a ~/.claude/projects/-Users-me-project-b

# Fuzzy match on project dir name (partial string)
session-compare swift-hawk warm-spruce

# With custom labels and output file
session-compare path1 path2 --label1 "Quick approach" --label2 "MDD approach" --output report.md
```

## Instructions

1. Identify both session paths. Ask the user if not clear from context. Common locations:
   - `~/.claude/projects/<escaped-path>/<uuid>.jsonl`
   - Or the project directory containing the `.jsonl`

2. Run the CLI:

```bash
session-compare <session1> <session2> --label1 "<name1>" --label2 "<name2>" --output /tmp/session-comparison.md
```

3. Read the output and present the metrics table to the user inline.

4. If the user wants the report saved to a project location, copy `/tmp/session-comparison.md` to the appropriate path.

## CLI reference

```
session-compare <session1> <session2> [options]

Arguments:
  session1, session2   .jsonl file, project directory, or partial project name

Options:
  --output <file>      Write to file instead of stdout
  --label1 <name>      Label for session 1 (default: filename stem)
  --label2 <name>      Label for session 2 (default: filename stem)
```

## Pricing model (claude-sonnet-4-6, baked in)

| Bucket      | $/MTok |
|-------------|--------|
| Input       | $3.00  |
| Cache read  | $0.30  |
| Cache write | $3.75  |
| Output      | $15.00 |

Opus 4.7 and Haiku 4.5 pricing is also baked in — model auto-detected from transcript.

## Example output (abbreviated)

```markdown
# Session Comparison: quick vs mdd

| | quick | mdd |
|---|---|---|
| Duration | 9m 50s | 57m 05s |
| Model | claude-sonnet-4-6 | claude-sonnet-4-6 |
| Human turns | 4 | 57 |
| Output tokens | 4.7K | 24.8K |
| Cache read tokens | 401K | 5,891K |
| Estimated cost | $0.19 | $2.16 |
| Cost ratio | — | 11.4x |
```

Attribution

tstaplertstapler
View sourceMore from tstapler →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →