Session Am — Development skill for Claude Code
Request text for the experiment session (agentic-microscope).
How to install Session Am
Installs to ~/.claude/skills/kyu-softmatter-sim-exp-bridge-session_am/SKILL.md
mkdir -p ~/.claude/skills/kyu-softmatter-sim-exp-bridge-session_am && curl -fsSL https://raw.githubusercontent.com/kyu-softmatter/sim-exp-bridge/HEAD/prompts/session_am.md -o ~/.claude/skills/kyu-softmatter-sim-exp-bridge-session_am/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Session Am does
Request text for the experiment session (agentic-microscope)
**Historical.** This is the text that was pasted into the microscope session to start the thread. It is kept as written except for translation and for counts that have since changed (the validator had seven rules then and has thirteen now). The thread has since run to r8; several implementation items below are done. Read `../README.md` for the current protocol.
Purpose
This is the work of connecting this reposito
Alternatives in Development
- Quick Plan — Create a detailed implementation plan based on the user's requirements provided through the USER_PROMPT variab 3.4k ★
- Agentlas Graph — Build an Agentlas automation by describing it, list saved ones, or request a run 1.1k ★
- Claude Balancer — A load balancer proxy for multiple Claude OAuth accounts with automatic failover, request tracking, and web da 910 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Session Bd
Request text for the simulation session (Brownian-Dynamics-Agent)
Gemini St
interactive google Gemini CLI interface for Sublime Text with file-context and agentic coding support
Muse:Andy Grove
Think with Andy Grove (interpretive frame) — adaptive structured session (v2.2) using the virtual-new-CEO thou
Xp Hint
Use the active XP session and request a hint from the real backend.
Claude Code Shadow Bill
Price your Claude Code transcripts at API list rates: request leaderboard, per-session costs, and the 60-minut
Argus Code
See what Claude Code actually did. Local-first observability for every session: which tools ran, what each sub
Related Agents
Fable Experimenter
Use this agent whenever Pulkit gives a new project/UI experiment prompt in the fable repo (a request to build
Autoresearch Orchestrator
Use this agent to run an autoresearch experiment session end-to-end — setup, baseline, and a batch of edit→mea
Pan Experiment Runner
Drives an external AI coding session against an experiment folder. Observation-only — read-only relative to PA