New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Claude Session Exporter

by sugarforever in sugarforever/01coder-agent-skills

Lists Claude Code session transcripts and exports them to organized Markdown with a digest, a clean conversation and linked tool-call details.

MITAuto-check passedProductivity & Automation

Install Claude Session Exporter

skills CLI
$ npx skills add sugarforever/01coder-agent-skills --skill claude-session-manager -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sugarforever/01coder-agent-skills claude-session-manager --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sugarforever/01coder-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude-session-manager .claude/skills/claude-session-manager && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claude-session-manager
GitHub stars
136
Token cost
~1.7k tokens
SKILL.md length
790 words
Files
3 (incl. scripts)
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Lists Claude Code session transcripts and exports them to organized Markdown with a digest, a clean conversation and linked tool-call details.

  • Works in 4 steps: Run a candidate list command. Use… → If the user gave a project hint, date,… → Present the numbered candidate rows to… → …
  • Exporting Claude Code session logs to readable Markdown
  • SKILL.md covers Overview, Quick Start, Specific Mode Candidate Flow and Output Layout, plus 3 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Claude Code keeps session transcripts as JSONL files under ~/.claude/projects, and this skill turns them into readable Markdown. A bundled Python script, scripts/manage_claude_sessions.py, lists candidate sessions or exports them into project-organized transcripts with a digest, a clean user and Claude conversation, and linked tool-call details.

Full mode exports every matching session, which suits archiving or backup, while specific mode lists numbered candidates first and exports only the one you pick. Filters narrow the set by project text, session text, a since date or a limit on the most recent sessions, and an option embeds full tool inputs and results inline instead of in a sidecar file. The default output folder is ~/.claude/session-markdown, and the agent tells you before exporting there.

When your agent uses it

  • Exporting Claude Code session logs to readable Markdown
  • Listing recent sessions to find the one that needs recovering
  • Archiving all sessions for a project as a backup
  • Summarizing the tool calls made during a past session

Example prompts

  • “Export all my Claude Code sessions for the billing project to Markdown.”
  • “List my 20 most recent Claude Code sessions so I can pick one to convert.”
  • “Convert the session from last Friday into Markdown with full tool details inline.”

Requirements

  • Python 3
  • Local Claude Code session files under ~/.claude/projects

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Run a candidate list command. Use --limit 20 by default unless the user asks for a different count.
  2. If the user gave a project hint, date, or session id fragment, pass it through the same filters
  3. Present the numbered candidate rows to the user. The candidate table includes modified time, project key, short session id, cwd, and first…
  4. After the user chooses a number, rerun with the exact same filters and --pick N

What it can do on your machine

Read from SKILL.md and the folder at commit e51fb6e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Session Exporter loads about 1.7k tokens when it runs. Until then it costs about 118 tokens; SKILL.md has 790 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~118
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from sugarforever/01coder-agent-skills at commit e51fb6e, republished under its MIT licence (© sugarforever). 790 words, ~1,698 tokens.

Download SKILL.mdSave it as .claude/skills/claude-session-manager/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
claude-session-manager
description
Manage Claude Code session transcripts from local JSONL storage, including listing candidate sessions, exporting full or selected sessions to organized Markdown, inspecting archives, and summarizing tool-call history. Use when the user asks to scan, parse, archive, inspect, recover, summarize, manage, or convert Claude Code sessions, `~/.claude/projects` data, `.jsonl` transcripts, tool-call history, or hard-to-read Claude Code conversation logs.

Claude Session Manager

Overview

Claude Code stores session transcripts as JSONL files under ~/.claude/projects/<project-key>/<session-id>.jsonl. Use the bundled manager to list candidates or export sessions into project-organized Markdown transcripts with a digest, a clean user/Claude conversation, and linked tool-call details.

Default output folder: ~/.claude/session-markdown. Tell the user before exporting there, and mention any custom output folder they requested.

Quick Start

Let the user's wording choose the mode when it is clear; otherwise ask them to choose before exporting:

  • Full mode: export all matching sessions. Use this for archive, backup, broad search, or "convert all sessions" requests.
  • Specific mode: list candidate sessions first, ask the user to pick one, then export only that session.

Run from any directory:

bash
python3 /path/to/claude-session-manager/scripts/manage_claude_sessions.py

Equivalent explicit form:

bash
python3 /path/to/claude-session-manager/scripts/manage_claude_sessions.py \
  --source ~/.claude/projects \
  --output ~/.claude/session-markdown

Useful options:

  • --mode full: export all matching sessions. This is the default.
  • --mode specific --list-candidates: print a numbered candidate table and do not export.
  • --mode specific --pick N: export the Nth candidate from the same filtered candidate list.
  • --project <text>: only export project folders whose key contains this text.
  • --session <text>: only export sessions whose id or filename contains this text.
  • --since YYYY-MM-DD: only export sessions modified on or after this date.
  • --limit N: export the N most recently modified matching sessions.
  • --include-tool-details-inline: embed full tool inputs/results in the main session Markdown. By default, the main transcript keeps compact collapsible tool summaries and links full payloads through the sidecar file.

Specific Mode Candidate Flow

Use this flow when the user wants one session, is unsure which session they need, or asks to inspect recent sessions before converting.

  1. Run a candidate list command. Use --limit 20 by default unless the user asks for a different count.
bash
python3 /path/to/claude-session-manager/scripts/manage_claude_sessions.py \
  --mode specific \
  --list-candidates \
  --limit 20
  1. If the user gave a project hint, date, or session id fragment, pass it through the same filters:
bash
python3 /path/to/claude-session-manager/scripts/manage_claude_sessions.py \
  --mode specific \
  --list-candidates \
  --project my-repo \
  --since 2026-06-01 \
  --limit 20
  1. Present the numbered candidate rows to the user. The candidate table includes modified time, project key, short session id, cwd, and first user prompt excerpt. These are the selection signals; do not ask the user to inspect raw JSONL paths.
  2. After the user chooses a number, rerun with the exact same filters and --pick N:
bash
python3 /path/to/claude-session-manager/scripts/manage_claude_sessions.py \
  --mode specific \
  --pick 3 \
  --limit 20

If the user already gives an exact session id or unique fragment, use --mode specific --session <id-or-fragment> --list-candidates first when there is any ambiguity. Export with --pick 1 only when the candidate list has exactly one match.

Show full SKILL.md (402 more words)Show less

Output Layout

The exporter writes:

text
~/.claude/session-markdown/
├── index.md
└── <project-key>/
    ├── index.md
    ├── <session-id>.md
    └── tool-details/
        └── <session-id>.tools.md

Keep the original Claude project key as the folder name. It is stable and avoids guessing at path decoding.

Each session Markdown includes:

  • Digest: source path, project key, session id, cwd, timestamps, event/message/tool counts, and first user prompt excerpt.
  • Linked tool details file when tool calls or results exist.
  • Timeline: all events are emitted under a ## Timeline section as numbered third-level headers in ISO-8601 format: ### N. user - <ISO> for user turns and ### N. assistant - <ISO> for assistant turns.
  • Message content in the main conversation should avoid Markdown heading syntax too; convert headings to bold lines outside code fences so regular Markdown readers do not render oversized headings inside the flow.
  • Compact tool references such as <tool_call_000001> Bash - command: npm test - result inside the relevant assistant turn, with matching sections in the sidecar details file by default.
  • Metadata and attachment events (### N. attachment - <ISO>, ### N. permission-mode, ### N. file-history-snapshot, ### N. last-prompt, etc.) and [thinking] blobs in assistant turns are emitted as their own numbered events in the timeline. Readers should skip them as noise; they do not carry conversation content.

Reading Exported Sessions

  • Read the main session Markdown first. The conversation and compact tool references should be enough to understand the flow.
  • Treat each <tool_call_000001> reference as a pointer into tool-details/<session-id>.tools.md.
  • Only open the tool details file when exact command input, file content, search results, or full tool output matters.
  • Do not load the whole sidecar by default for large sessions; search for the specific tool reference.

Workflow

  1. Confirm the source folder. Default to ~/.claude/projects.
  2. Ask the user to choose full mode or specific mode if they did not already make the choice.
  3. Confirm or announce the output folder. Default to ~/.claude/session-markdown.
  4. For full mode, run the exporter script with any needed filters.
  5. For specific mode, list candidates, get the user's chosen number, then export with --pick.
  6. Report the number of sessions exported, output index path, and any parse warnings.
  7. If the user wants a specific session explained, read the generated Markdown first; load the sidecar tool details only when exact tool inputs/results matter.

Notes

  • Treat transcript data as private. It can contain prompts, file contents, command output, secrets accidentally pasted into chat, and tool results.
  • Do not delete or modify original .jsonl files.
  • Prefer sidecar tool details for large sessions. Inline tool payloads can make Markdown hard to search and load.

© sugarforever, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/claude-session-manager of sugarforever/01coder-agent-skills.

  • SKILL.md
  • agents/openai.yaml
  • scripts/manage_claude_sessions.py

Open the folder on GitHubat commit e51fb6e

Compare with similar skills

Claude Session Exporter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claude Session Exporter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Session Exporter this skillsugarforever/01coder-agent-skills136—~1.7kAutomated safety check: PassMIT
Web To Markdownrookie-ricardo/erduo-skills935—~894Automated safety check: PassMIT
XiaoyaoSearch Local File Searchdtsola/xiaoyaosearch1k—~836Automated safety check: PassCustom licence
Web Page ReaderHKUDS/Vibe-Trading35k—~627Automated safety check: PassMIT
Defuddlekepano/obsidian-skills49k12 repos~208Automated safety check: PassMIT
Disk Storage AnalyzerKKKKhazix/khazix-skills21k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Web To Markdown

    rookie-ricardo/erduo-skills

    Convert a web URL into cleaned Markdown with deterministic routing.

    935 GitHub stars~894 tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed

  • XiaoyaoSearch Local File Search

    dtsola/xiaoyaosearch

    Searches local files from an agent through the XiaoyaoSearch MCP server, using semantic, full-text, hybrid, image-similarity and voice queries.

    1k GitHub stars~836 tokensUpdated 6 days ago
    Productivity & AutomationAuto-check passed

  • Web Page Reader

    HKUDS/Vibe-Trading

    Converts web pages, articles and documentation links into clean Markdown through the read_url tool, which sends the full URL to the third-party Jina Reader service.

    35k GitHub stars~627 tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Defuddle

    kepano/obsidian-skills

    Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens.

    49k GitHub starsUsed in 12 repos~208 tokens
    Knowledge ManagementAuto-check passed

  • Disk Storage Analyzer

    KKKKhazix/khazix-skills

    Scans a Mac or Windows PC read-only to find what fills the disk, grades each item by how safe it is to clean and builds an interactive HTML report.

    21k GitHub starsUsed in 1 repo~1.4k tokens
    Productivity & AutomationAuto-check passed

  • URL to Markdown Fetcher

    JimLiu/baoyu-skills

    Fetches a web page, X post, YouTube transcript or Hacker News thread through a Chrome-driven CLI and saves it as clean markdown.

    26k GitHub starsUsed in 2 repos~2.1k tokens
    Knowledge ManagementAuto-check passed

More from sugarforever/01coder-agent-skills

All 21 skills in this repo

  • Typography Cover Designer

    sugarforever/01coder-agent-skills

    Designs typography-driven video covers and thumbnails in HTML/CSS and screenshots them with Chrome DevTools at 16:9, 16:10, 9:16 and 3:4.

    136 GitHub stars~3.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Mining Session Skills

    sugarforever/01coder-agent-skills

    Reviews one finished Claude Code session from its exported markdown and decides whether a skill is worth creating, updating or reusing for similar work.

    136 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed

  • Subtitle Correction

    sugarforever/01coder-agent-skills

    Fixes speech-recognition mistakes in .srt subtitle files, in Chinese or English, using terms you supply and leaving every timestamp untouched.

    136 GitHub stars~2.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Codex Session Manager

    sugarforever/01coder-agent-skills

    Lists, filters and exports local Codex session transcripts to organized Markdown with a digest, timeline and tool-call details, in full or pick-one mode.

    136 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

  • Diagram to Image Converter

    sugarforever/01coder-agent-skills

    Converts Mermaid diagrams and markdown tables into PNG images through a hosted rendering API, for platforms without rich formatting.

    136 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed

  • Audio and SRT to Narrated Video

    sugarforever/01coder-agent-skills

    Builds a narration-synced MP4 from a voiceover audio file and its SRT subtitles using HyperFrames, with scenes timed to the subtitle cues; instructions are in Chinese.

    136 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Claude Session Exporter

What does Claude Session Exporter do?

Lists Claude Code session transcripts and exports them to organized Markdown with a digest, a clean conversation and linked tool-call details. claude/projects, and this skill turns them into readable Markdown.py, lists candidate sessions or exports them into project-organized transcripts with a digest, a clean user and Claude conversation, and linked tool-call details.

When should I use Claude Session Exporter?

Claude Session Exporter fits situations like: exporting Claude Code session logs to readable Markdown; listing recent sessions to find the one that needs recovering; archiving all sessions for a project as a backup; summarizing the tool calls made during a past session.

How do I install Claude Session Exporter in Claude Code?

Run `npx skills add sugarforever/01coder-agent-skills --skill claude-session-manager -a claude-code`. Or copy the skill folder (skills/claude-session-manager in sugarforever/01coder-agent-skills) into .claude/skills/claude-session-manager in your project. Claude Code loads it when a task matches its description.

How do I install Claude Session Exporter in Codex?

Run `npx skills add sugarforever/01coder-agent-skills --skill claude-session-manager -a codex`. Or copy the skill folder (skills/claude-session-manager in sugarforever/01coder-agent-skills) into .agents/skills/claude-session-manager in your project. Codex loads it when a task matches its description.

Can I use Claude Session Exporter in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sugarforever/01coder-agent-skills --skill claude-session-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-session-manager, .gemini/skills/claude-session-manager, .github/skills/claude-session-manager and .opencode/skills/claude-session-manager in your project.

What does Claude Session Exporter need to run?

Going by SKILL.md and its folder, Claude Session Exporter needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; Local Claude Code session files under ~/.claude/projects.

Does Claude Session Exporter access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Claude Session Exporter safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Claude Session Exporter use?

Claude Session Exporter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Claude Session Exporter use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claude Session Exporter?

Skills that share tags, products or a category with Claude Session Exporter: Web To Markdown (rookie-ricardo/erduo-skills, 935 stars), XiaoyaoSearch Local File Search (dtsola/xiaoyaosearch, 1k stars), Web Page Reader (HKUDS/Vibe-Trading, 35k stars) and Defuddle (kepano/obsidian-skills, 49k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Session Exporter?

sugarforever (a GitHub user) maintains it in sugarforever/01coder-agent-skills, which has 136 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on June 19, 2026.

Source: sugarforever/01coder-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.