TypingMindTypingMindThe best frontend for AI
Session Trace logo

Session Trace

Organization
greenfield-inc
session-trace

Publish an agent session as a readable trace page in Grain, with the story, key moments, every request and step on a timeline, subagents, and the pull requests it opened. Use when asked for a trace or "how did this run go", or when a task already has a Grain page (for example from prepare-pr or handoff).

Overview

Publishergreenfield-inc
RepositoryPane
Skill namesession-trace
Stars
529
Forks
227
Bundled files
2
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by greenfield-inc on GitHub. Read the source before you install it.

Installation

Install the Session Trace AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/greenfield-inc/Pane/tree/main/main/src/services/paneChatBundle/skills/session-trace
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/greenfield-inc/Pane.git /tmp/Pane
mkdir -p .claude/skills
cp -r /tmp/Pane/main/src/services/paneChatBundle/skills/session-trace .claude/skills/session-trace
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Session Trace in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Session Trace on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Session Trace is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Session trace

Turn a session into a page someone who wasn't there can read in five minutes: what was asked, what happened, where it went right or wrong, and what came out of it. A raw log is the evidence, not the page.

Read references/page-guide.md first. It says what the page must answer, what to capture beyond the trace, and how to lay it out. scripts/build-trace.mjs is a working starting point for Claude Code and Codex logs. Adapt it, or build the same page shape another way, when a harness or task needs something else.

When to run

  • When the user asks for a trace, a run review, or a page they can share about a session.
  • Without being asked, only when the task already has a Grain page (a PR companion from prepare-pr, or a handoff page), or the session opened a pull request. Then attach the trace to that page. Don't run it after every session.

Steps

  1. Find the session log.
    • Claude Code: ~/.claude/projects/<project>/$CLAUDE_CODE_SESSION_ID.jsonl, with subagents under <session id>/subagents/.
    • Codex: the newest ~/.codex/sessions/**/rollout-*.jsonl whose first line (session_meta) has this working directory and no parent_thread_id. Its subagents are the rollouts whose parent_thread_id is its id.
    • The script finds both on its own; pass --session FILE to choose.
    • Other harnesses: see "Other harnesses" in the page guide.
  2. Read the session for the story. Run node scripts/build-trace.mjs --out <tmp> --outline to list every request with its anchor (t0, t1, …). Use what you remember of the session plus that outline to write story.json: a plain summary and 4–8 key moments, as described in the guide.
  3. Build the page. Run node scripts/build-trace.mjs --out <dir> --story story.json --title "<task>: session trace" --back index.html. This writes trace.html and trace.otlp.json (OpenTelemetry spans). Open the page and check the story, the moments, and that the PRs you know about are listed. Add missing PRs, releases, or artifacts by hand or by extending the script.
  4. Review before publishing. The page shows every user message in full, including anything pasted (meeting notes, logs, customer text). Only emails and tokens are redacted automatically. Remove or trim anything the page's readers shouldn't see, and ask when unsure.
  5. Publish with Grain's installed skill when Grain is connected. Otherwise save trace.html in the page bundle (see page) and report its path.
    • Add the page to the task's existing Grain workspace and link it from that workspace's main page, near the top.
    • With no existing page, create one in Development Artifacts/<org>/<repo>, named for the task.
    • Keep it private. Never create or widen a share. If the workspace already has a public share, tell the user the trace will be visible through it before you push.
  6. Report the link, and anything you left out or couldn't capture.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Session Trace AI skill do?

Publish an agent session as a readable trace page in Grain, with the story, key moments, every request and step on a timeline, subagents, and the pull requests it opened. Use when asked for a trace or "how did this run go", or when a task already has a Grain page (for example from prepare-pr or handoff).

Why use Session Trace on TypingMind?

Because you install it once and use it with any model. Session Trace is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Session Trace in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/greenfield-inc/Pane/tree/main/main/src/services/paneChatBundle/skills/session-trace. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Session Trace?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Session Trace?

As many as you like. As long as a model supports skills, you can use Session Trace with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Session Trace AI skill free?

It is published on GitHub by greenfield-inc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Discrawl

openclaw
OrganizationPopular

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

82.2K
391K
1 files
View
openclaw logo

Gitcrawl

openclaw
OrganizationPopular

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

82.2K
391K
1 files
View
openclaw logo

Graincrawl

openclaw
OrganizationPopular

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

82.2K
391K
1 files
View
openclaw logo

Openclaw Changelog Update

openclaw
OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

82.2K
391K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇