session-finder

This skill should be used when the user wants to find, search, or resume previous Claude Code sessions based on conversation content, files edited, or tools used. Use this skill when the user asks to find sessions where they worked on specific topics, edited particular files, or used certain tools.

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/jnarowski/agentcmd/session-finder
Any agent
npx skills add jnarowski/agentcmd --skill session-finder
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00062 $0.01497
Opus 5 $0.00031 $0.00749
Sonnet 5 $0.00012 $0.00299
Haiku 4.5 $0.00006 $0.00150

Measured today against content hash 6326e9ed06a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-finder 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/search_sessions.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.

.claude/skills/session-finder/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Finder

Overview

This skill enables searching through Claude Code session history to find previous conversations based on actual content, not just metadata. It provides accurate search results by parsing session JSONL files and ranking matches by relevance score.

When to Use This Skill

Use this skill when the user requests:

  • "Find sessions where I worked on [topic]"
  • "Search for sessions that edited [filename]"
  • "Show me sessions about [feature/bug/task]"
  • "Find when I used [tool name]"
  • "Resume the session where I worked on [something]"

Quick Start

To search sessions, execute the scripts/search_sessions.py script:

python3 scripts/search_sessions.py "search terms" [optional-project-path]

Examples:

# Search current project for Pino log rotation work
python3 scripts/search_sessions.py "pino log rotation"

# Search specific project for authentication sessions
python3 scripts/search_sessions.py "authentication JWT" /Users/username/Dev/myproject

# Find sessions that edited config files
python3 scripts/search_sessions.py "config.ts"

# Find WebSocket-related work
python3 scripts/search_sessions.py "websocket refactor"

How It Works

Search Process

  1. Parse search terms - Split the search description into keywords
  2. Locate session directory - Find the Claude sessions directory for the project
  3. Scan JSONL files - Parse each session file line-by-line
  4. Filter content - Search only message.content fields (not metadata)
  5. Score matches - Rank results by relevance:
    • Tool name matches: +2 points
    • Tool input matches: +1 point
    • Text content matches: +1 point per keyword
    • Tool result matches: +0.5 points
  6. Display results - Show top 5 sessions with context and resume commands

What Gets Searched

Included (high-value signals):

  • Message text content (user and assistant messages)
  • Tool names (Read, Write, Edit, Bash, etc.)
  • Tool inputs (file paths, command arguments, etc.)
  • Tool results (command output, file content, etc.)

Read the full file on GitHub · 208 lines

Files

What ships with it

3 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. today First seen · 208 lines · 62 tokens per session scan A 6326e9ed06a6

Subscribe to this mod's changes

session-finder is a skill published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 62 tokens to every session and 1,497 once invoked, about $0.0003 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 2026-09-01.

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