robertsfeir

robertsfeir/atelier-pipeline

Hook Claude Code

Runs when a subagent starts, executing log-agent-start.sh. From robertsfeir/atelier-pipeline.

robertsfeir/atelier-pipeline

Hook Claude Code

Runs when a session starts, executing session-boot.sh. From robertsfeir/atelier-pipeline.

robertsfeir/atelier-pipeline

Hook Claude Code

Runs when a subagent finishes, executing log-agent-stop.sh, enforce-colby-stop-verify.sh, enforce-brain-capture-pending.sh and prompt-compact-advisory.sh (4 commands). From robertsfeir/atelier-pipeline.

robertsfeir/atelier-pipeline

Hook Claude Code

Runs after a tool call finishes, executing clear-brain-capture-pending.sh. From robertsfeir/atelier-pipeline.

robertsfeir/atelier-pipeline

Hook Claude Code

Runs before the context is compacted, executing pre-compact.sh. From robertsfeir/atelier-pipeline.

robertsfeir/atelier-pipeline

Hook Claude Code

Runs after the context is compacted, executing post-compact-reinject.sh. From robertsfeir/atelier-pipeline.

robertsfeir/atelier-pipeline

Hook Claude Code

Runs on the StopFailure event, executing log-stop-failure.sh. From robertsfeir/atelier-pipeline.

robertsfeir/atelier-pipeline

Settings file Claude Code

Agent settings declaring 8 hook events (PreToolUse, SubagentStart, SessionStart, SubagentStop) and 10 allowed tools.

robertsfeir/atelier-pipeline

Cursor rule

Cursor rule "agent-discovery" from robertsfeir/atelier-pipeline, covering agent discovery, core agent constant, discovery protocol, conflict detection and brain persistence for routing preferences.

robertsfeir/atelier-pipeline

Cursor rule

Every agent follows these steps at the start and end of every work unit. Agent-specific cognitive directives and domain-specific actions remain in each agent's persona file.

robertsfeir/atelier-pipeline

Cursor rule

Cursor rule "agent-system" from robertsfeir/atelier-pipeline, covering brain configuration, architecture, skills (main thread), subagents (own context window) and eva -- the central nervous system.

robertsfeir/atelier-pipeline

Cursor rule

Branch lifecycle rules -- loaded when working with pipeline state.

robertsfeir/atelier-pipeline

Cursor rule

When the pipeline uses an MR-based branching strategy (GitHub Flow, GitLab Flow, GitFlow), Eva creates the branch and worktree at pipeline start. Colby handles MR creation.

robertsfeir/atelier-pipeline

Cursor rule

Sarah reads this file when the task involves cloud deployment, Terraform, or infrastructure design. This is NOT loaded for normal application architecture work.

robertsfeir/atelier-pipeline

Cursor rule

Cursor rule "default-persona" from robertsfeir/atelier-pipeline, covering default persona: eva, what this means, always-loaded context, session boot sequence (run on every new session) and context eviction (post-boot).

robertsfeir/atelier-pipeline

Cursor rule

This document is the single source of truth for design system detection, selective loading, cross-agent consistency, and icon handling. Agent personas reference this doc rather than duplicating the rules inline.

robertsfeir/atelier-pipeline

Cursor rule

Cursor rule "dor-dod" from robertsfeir/atelier-pipeline, covering definition of ready / definition of done, how it works, dor and dod inside, dor: requirements extracted and dod: verification.

robertsfeir/atelier-pipeline

Cursor rule

Run a full-spectrum, multi-agent audit covering every layer of the application: architecture, implementation, testing, security, frontend/UX, product alignment, and blind code review. All rounds run in parallel — contamination is prevented by instruction, not by timing. Phase 2 begins only after all active rounds…

robertsfeir/atelier-pipeline

Cursor rule

Cursor rule "invocation-templates" from robertsfeir/atelier-pipeline, covering invocation templates, shared protocols (apply to all templates below), template index, sarah (adr production) and sarah (large adr -- with research brief).

robertsfeir/atelier-pipeline

Cursor rule

Loads automatically when Eva reads {pipelinestatedir}/ files. Model and effort assignment follows a 4-tier task-class model: the agent's task class determines the base model + effort pair, and a small set of promotion signals adjust effort by exactly one rung. Eva sets both parameters explicitly in every Agent tool…

robertsfeir/atelier-pipeline

Cursor rule

Eva reads this file at pipeline start for detailed operational procedures.

robertsfeir/atelier-pipeline

Cursor rule

Loads automatically when Eva reads {pipelinestatedir}/ files. Contains ALWAYS-loaded content: mandatory gates, brain capture model, pipeline flow, agent standards, terminal transition. JIT sections load from sibling reference files on the triggers listed below.

robertsfeir/atelier-pipeline

Cursor rule

JIT-loaded sections extracted from pipeline-orchestration.md. Eva loads this file on demand per the triggers in that file's Loading Strategy table.

robertsfeir/atelier-pipeline

Cursor rule

Loaded by Eva when she encounters an ambiguous routing case outside an active pipeline, when a discovered agent appears to overlap a core agent, or when smart-context detection needs to run against the full artifact table. The inline summary in .cursor/rules/agent-system.md covers the common cases and points here for…