chronicle

skills

Agent plugins and skills for working with the Chronicle experiment platform.

These skills help your agent track research hypotheses and experimental results, and provide role-filtered search over past experimental results and uploaded research documents. Hypotheses become first-class experiments; variations and runs record what was tried and what it produced — metrics, datasets, figures, write-ups, always including what didn't work. Search respects your role's access: you find everything you're allowed to see and nothing you aren't. And lineage travels with the record — parents, retractions, invalidated outputs — so new work builds on results whose provenance and current standing are explicit.

This repo is a marketplace for Claude Code and Codex (methodic) containing one plugin (chronicle).

Getting started

Quick start (TL;DR). The default path is UI first, then the plugin: create an account + API key in the Methodic UI, paste its one-line setup command (plus one pip install) in your terminal, install the plugin from the marketplace — and you're working.

# 1. UI: sign up at https://methodiclabs.ai/chronicle/signup, open
#    "API keys" in the sidebar, create a key, and paste the one-line
#    setup command the UI shows. It looks like:
mkdir -p ~/.methodic && echo 'api_key: sk_user_...' > ~/.methodic/credentials.yaml && chmod 600 ~/.methodic/credentials.yaml
# …optional: install the SDK (only for large/multi-file uploads + W&B):
pip install methodic-research

# 2. Claude Code: install the plugin from the marketplace.
/plugin marketplace add methodic-research/skills
/plugin install chronicle

# Codex equivalent:
codex plugin marketplace add methodic-research/skills
codex plugin add chronicle@methodic

That's the whole default path — once the plugin is installed you can start immediately ("survey the literature on …", "propose an experiment for …"). The pip install is now optional: the plugin bundles an MCP server (step 3) that talks to Chronicle directly, so most skills work with no Python. Install methodic-research only for the SDK-only paths (large/multi-file dataset uploads, agent-side W&B). Details below.

Heads-up for agents (initial bootstrap). Creating the account and API key happens in the Methodic UI, logged in as the user — there is no API an agent can call to bootstrap credentials it doesn't yet have (no key, no JWT → no access). If ~/.methodic/credentials.yaml is missing, ask the user to do step 1 below — create a key in the UI and run the one-line setup command it shows in their terminal — then retry. Don't ask for the raw key in chat. The files that command writes are the same credentials everything here reads: the skills/SDK, the MCP Authorization header, and direct REST calls.

1. Create an account and API key (the Methodic UI)

Everything starts in the Methodic UI — the one step only you can do (initial bootstrap — an agent can't do it for you; see the note above):

1. Create an account at methodiclabs.ai/chronicle/signup (or sign in if you already have one).

2. Create an API key: open API keys in the sidebar and create one. If you work in an organization, create the key in that organization's context — the setup command then records the org as your default; create it in your personal context otherwise.

3. Paste the one-line setup command the UI shows into your terminal — one paste, no environment variables. It writes the standard ~/.methodic client config that Chronicle.from_env() reads, and everything here uses the same files: skills/SDK, the MCP Authorization header, and direct REST calls. It looks like:

   # Key created in your personal context:
   mkdir -p ~/.methodic && echo 'api_key: sk_user_...' > ~/.methodic/credentials.yaml && chmod 600 ~/.methodic/credentials.yaml
   
   # Key created in an organization context — additionally records that org:
   mkdir -p ~/.methodic && echo 'organization_id: <org-principal-id>' > ~/.methodic/config.yaml && echo 'api_key: sk_user_...' > ~/.methodic/credentials.yaml && chmod 600 ~/.methodic/credentials.yaml
   

4. (Optional) Install the SDK — the bundled MCP server (step 3) handles most skills with no Python at all. Install methodic-research only for the SDK-only paths: large / multi-file directory dataset uploads (chronicle.datasets.upload shards a directory; the MCP upload_asset is single-blob) and agent-side W&B fetch. Skills prefer the SDK when it's importable, and fall back to the MCP tools otherwise: