blitz-cli 0.7.0

Developer CLI for Blitz locker-room: spec-driven playbooks, a codebase/huddle ontology graph with an MCP tool, and the composable watcher/trainer/graph containers.

blitz-cli

Developer CLI for the Blitz locker-room: spec-driven playbooks for your coding agent, a local ontology graph of your codebase/huddles/features (served to agents over MCP), and the composable containers that keep it fresh.

pip install blitz-cli

The core CLI is stdlib plus rich. Two optional extras carry heavier deps only when you need them: blitz-cli[locker-room] (the MCP server) and blitz-cli[train] (the QLoRA trainer).

Top-level commands: playbooks, locker-room, activity.

Playbooks: spec-driven development commands

blitz playbooks init installs a set of spec-driven-development slash-commands into a repo, rendered for whichever agent you use (Claude Code, Cursor, GitHub Copilot, Gemini CLI, OpenCode), plus a shared .playbooks/ working area.

blitz playbooks init                 # auto-detect the agent(s) in this repo
blitz playbooks init --agent claude  # or target one explicitly
blitz playbooks init --all           # install for every supported agent

The commands are specify, plan, tasks, implement, playbook, clarify, and analyze. Run at a folder of repos, init installs into each repo it finds (recursing through non-git folders) and adds a workspace-level /huddle command for coordinating a feature across repos. Use --ignore PATH to skip a repo and --root to force a single install.

Locker-room: ontology graph, watcher, trainer, MCP

blitz locker-room init scaffolds a docker-compose.yml that pulls prebuilt images (from sparepartslabs/blitz-locker-room, pinned to this CLI version) for three roles sharing ./data:

• watch: ingests your coding agent's session transcripts into a corpus.
• graph: rebuilds an ontology of your playbook-enabled repos, huddles, features, and their code lineage into data/ontology.db on a loop.
• mcp: serves that ontology to agents over SSE.

blitz locker-room init          # write ./locker-room/docker-compose.yml
cd locker-room
blitz locker-room up            # start watch + graph + mcp
blitz locker-room logs

The ontology is also usable directly on the host, no containers required:

blitz locker-room ontologize    # scan a workspace into ./data/ontology.db
blitz locker-room list          # list playbook-enabled repos + their active feature
blitz locker-room mcp           # stdio MCP server for a local agent

The graph an agent can query

ontologize reuses playbook discovery and static code parsing (Python symbols + imports + calls; File nodes for other languages) to build a graph of Workspace, Repo, AgentTool, Playbook, Feature (with lifecycle stage), Huddle, File, and Symbol nodes. Each feature's git branch diff links it to the code it touches (Feature -TOUCHES-> File/Symbol), so an agent can walk a spec out to the full lineage of code it implements, and back. The MCP tools expose this: list_repos, get_repo, list_huddles, get_huddle, get_playbooks, get_lineage, impact_of, get_file, get_symbol, and a generic neighbors.

Training (optional)

blitz locker-room train runs an on-demand QLoRA fine-tune of the watcher corpus in the trainer container (needs a GPU); adapters land in ./train-out. Override the base model with BASE_MODEL_HF or blitz locker-room init --base-model.

Activity: replay a coding-agent session

blitz activity reads your coding agent's own local session transcripts (currently Claude Code's, at ~/.claude/projects) for the current repo and replays each prompt alongside the actions taken to resolve it (tool calls, sub-agents) and the final response:

blitz activity --list               # sessions for this repo, most recent first
blitz activity                      # the most recent session's timeline
blitz activity <session-id-prefix>  # a specific session
blitz activity --full               # untruncated prompts/responses/tool I/O
blitz activity --html report.html   # also write a self-contained HTML report

The terminal view is compact by default; --full shows untruncated text. The HTML report includes each action's full tool input/output, collapsed per action. Each turn shows its raw token usage and, where a pre-edit backup exists, a real diff of what an Edit/Write changed. Point at a different transcript root with --sessions-dir. This only reads local session data, no project id or API key.