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 Code Auto-Capture Hook

by NateBJones-Projects in NateBJones-Projects/OB1

Fires a Stop hook that captures a Claude Code session transcript automatically when the session ends without a verbal wrap-up.

Custom licenceAuto-check: notesAgent Workflows

Install Claude Code Auto-Capture Hook

skills CLI
$ npx skills add NateBJones-Projects/OB1 --skill auto-capture-claude-code -a claude-code

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

GitHub CLI
$ gh skill install NateBJones-Projects/OB1 auto-capture-claude-code --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/NateBJones-Projects/OB1.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/auto-capture-claude-code .claude/skills/auto-capture-claude-code && 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
auto-capture-claude-code
GitHub stars
4.7k
Token cost
~1.3k tokens
SKILL.md length
628 words
Files
4
Skills in repo
24
Repo updated
First seen
Licence
Custom licence

At a glance

Fires a Stop hook that captures a Claude Code session transcript automatically when the session ends without a verbal wrap-up.

  • Works in 4 steps: Claude Code fires a Stop hook at session… → The hook script… → The formatted transcript is POSTed to… → …
  • Capturing every meaningful Claude Code session without remembering to say wrap up
  • SKILL.md covers Relationship to Upstream Skill, Problem, What This Adapter Adds and How It Works, plus 5 more sections
  • Runs JavaScript scripts from its folder; needs MCP_ACCESS_KEY

What it does

This skill complements a separate upstream auto-capture skill that only fires on a verbal trigger like wrap up, by reading the transcript path and session metadata Claude Code passes to its Stop hook, then filtering, formatting, and sending the content to a knowledge-base ingest endpoint for automatic thought extraction.

It skips sessions with fewer than three user turns, agent-only sessions, sessions matching sensitivity patterns, and non-terminal end reasons like clear or resume, and saves a failed capture to a local retry queue that retries on the next session end, so a dropped network call doesn't silently lose a session.

When your agent uses it

  • Capturing every meaningful Claude Code session without remembering to say wrap up
  • Recovering a session that ended by closing the terminal or hitting Ctrl+C
  • Setting up automatic transcript capture to a knowledge base

Example prompts

  • “Set up automatic session capture so I don't have to say wrap up every time.”
  • “Why didn't my last session get captured?”
  • “Install the Claude Code adapter for auto-capture.”

Requirements

  • The upstream auto-capture skill installed first
  • An Open Brain ingest endpoint

Workflow steps

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

  1. Claude Code fires a Stop hook at session end, passing the transcript path
  2. The hook script (session-end-capture.mjs) reads the transcript, filters out
  3. The formatted transcript is POSTed to the Open Brain REST ingest endpoint
  4. Failed captures are saved to a local retry queue and retried on subsequent

What it can do on your machine

Read from SKILL.md and the folder at commit 238df6c. 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 script files (JavaScript), which the agent can run.

    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 these keys or tokens, usually read from environment variables:

    • MCP_ACCESS_KEY

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

Context cost

Claude Code Auto-Capture Hook loads about 1.3k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 628 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:92
    3. Set environment variables (in `.env.local` or your environment):

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); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 628 words (~1,338 tokens).

“This adapter implements the session-end capture behavior defined by the upstream auto-capture skill by Jared Irish. The base skill is a behavioral protocol — it describes when and what to capture during interactive session closes. This adapter is the concrete…”

— opening of SKILL.md by NateBJones-Projects, Custom licence
name
auto-capture-claude-code
author
Alan Shurafa
version
1.0.0
requires_skills
auto-capture

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files in skills/auto-capture-claude-code of NateBJones-Projects/OB1.

  • SKILL.md
  • README.md
  • metadata.json
  • session-end-capture.mjs

Open the folder on GitHubat commit 238df6c

Compare with similar skills

Claude Code Auto-Capture Hook 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 Code Auto-Capture Hook compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Code Auto-Capture Hook this skillNateBJones-Projects/OB14.7k—~1.3kAutomated safety check: NotesCustom licence
Memori MCP Memory UsageMemoriLabs/Memori17k—~3.8kAutomated safety check: PassMIT
Ourmemourmem/omem1741 repos~3.4kAutomated safety check: PassCustom licence
Agent RecallGoldentrii/AgentRecall-X371—~5.2kAutomated safety check: NotesMIT
Engram MemoryPatdolitse/piia-engram162—~1.3kAutomated safety check: PassAGPL-3.0-or-later
Compartment Session SweepMaxFreedomPollard/Compartment578—~750Automated safety check: PassApache-2.0

Similar skills

  • Memori MCP Memory Usage

    MemoriLabs/Memori

    Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.

    17k GitHub stars~3.8k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed

  • Ourmem

    ourmem/omem

    Shared memory that never forgets. An agent skill from ourmem/omem.

    174 GitHub starsUsed in 1 repo~3.4k tokens
    Agent WorkflowsAuto-check passed

  • Agent Recall

    Goldentrii/AgentRecall-X

    Persistent compounding memory for AI agents. An agent skill from Goldentrii/AgentRecall-X.

    371 GitHub stars~5.2k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check: notes

  • Engram Memory

    Patdolitse/piia-engram

    Routes continuity and recall requests to Engram, a local-first MCP memory and identity layer that saves user-approved lessons, decisions and playbooks.

    162 GitHub stars~1.3k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed

  • Compartment Session Sweep

    MaxFreedomPollard/Compartment

    Sweeps a conversation before compaction and saves durable facts, decisions and session records into the Compartment encrypted memory vault as short one-claim memories.

    578 GitHub stars~750 tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed

  • Memory Search

    thedotmack/claude-mem

    Searches the claude-mem database of past sessions in layers (index, timeline, full details) to find how a problem was solved before.

    98k GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from NateBJones-Projects/OB1

All 24 skills in this repo

  • Heavy File Ingestion

    NateBJones-Projects/OB1

    Converts large PDF, DOCX, PPTX, XLSX and CSV files into markdown or CSV plus an index before the agent reads them, so tokens go to the compressed copy.

    4.7k GitHub stars~995 tokensUpdated yesterday
    Auto-check passed

  • Aiception Skill Extraction

    NateBJones-Projects/OB1

    Pulls reusable knowledge out of work sessions and turns it into new skills, checking existing notes and skills first to avoid duplicates.

    4.7k GitHub stars~2k tokensUpdated yesterday
    Auto-check: notes

  • Open Brain Local HTTP

    NateBJones-Projects/OB1

    Captures and searches personal notes in a self-hosted Open Brain using plain curl calls over HTTP, for setups where MCP is disabled or blocked.

    4.7k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check: notes

  • Panning for Gold

    NateBJones-Projects/OB1

    Processes voice transcripts and brain dumps in three phases, extracting every idea thread, evaluating the strongest and saving a permanent inventory and synthesis.

    4.7k GitHub stars~5k tokensUpdated yesterday
    Auto-check passed

  • Agentic Harness Design and Review

    NateBJones-Projects/OB1

    Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.

    4.7k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Weekly Signal Diff

    NateBJones-Projects/OB1

    Turns a noisy week of AI or software market news into a short list of structural changes, weighted by what the user already tracks in Open Brain memory.

    4.7k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Claude Code Auto-Capture Hook

What does Claude Code Auto-Capture Hook do?

Fires a Stop hook that captures a Claude Code session transcript automatically when the session ends without a verbal wrap-up. This skill complements a separate upstream auto-capture skill that only fires on a verbal trigger like wrap up, by reading the transcript path and session metadata Claude Code passes to its Stop hook, then filtering, formatting, and sending the content to a knowledge-base ingest endpoint for automatic thought extraction.

When should I use Claude Code Auto-Capture Hook?

Claude Code Auto-Capture Hook fits situations like: capturing every meaningful Claude Code session without remembering to say wrap up; recovering a session that ended by closing the terminal or hitting Ctrl+C; setting up automatic transcript capture to a knowledge base.

How do I install Claude Code Auto-Capture Hook in Claude Code?

Run `npx skills add NateBJones-Projects/OB1 --skill auto-capture-claude-code -a claude-code`. Or copy the skill folder (skills/auto-capture-claude-code in NateBJones-Projects/OB1) into .claude/skills/auto-capture-claude-code in your project. Claude Code loads it when a task matches its description.

How do I install Claude Code Auto-Capture Hook in Codex?

Run `npx skills add NateBJones-Projects/OB1 --skill auto-capture-claude-code -a codex`. Or copy the skill folder (skills/auto-capture-claude-code in NateBJones-Projects/OB1) into .agents/skills/auto-capture-claude-code in your project. Codex loads it when a task matches its description.

Can I use Claude Code Auto-Capture Hook 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 NateBJones-Projects/OB1 --skill auto-capture-claude-code -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-capture-claude-code, .gemini/skills/auto-capture-claude-code, .github/skills/auto-capture-claude-code and .opencode/skills/auto-capture-claude-code in your project.

What does Claude Code Auto-Capture Hook need to run?

Going by SKILL.md and its folder, Claude Code Auto-Capture Hook needs JavaScript for the scripts in its folder and credentials named MCP_ACCESS_KEY. Our summary lists: The upstream auto-capture skill installed first; An Open Brain ingest endpoint.

Does Claude Code Auto-Capture Hook 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 Code Auto-Capture Hook safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Claude Code Auto-Capture Hook use?

Claude Code Auto-Capture Hook has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Claude Code Auto-Capture Hook use?

About 1.3k tokens (SKILL.md is roughly 5.4k 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 Code Auto-Capture Hook?

Skills that share tags, products or a category with Claude Code Auto-Capture Hook: Memori MCP Memory Usage (MemoriLabs/Memori, 17k stars), Ourmem (ourmem/omem, 174 stars), Agent Recall (Goldentrii/AgentRecall-X, 371 stars) and Engram Memory (Patdolitse/piia-engram, 162 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Code Auto-Capture Hook?

NateBJones-Projects (a GitHub organization) maintains it in NateBJones-Projects/OB1, which has 4,696 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 7, 2026.

Source: NateBJones-Projects/OB1 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.