yellow-core

Plugin yellow-core from marketplace yellow-plugins in KingInYellows/yellow-plugins. Commands read from the repo's manifest — today.

Skills (23)

• agent-native-architecture

  Reference for agent-native architecture principles: action parity, context parity, shared workspace, primitives over workflows, and dynamic context injection. Use when authoring agent integrations or designing tool surfaces.

• agent-native-audit

  Audit checklist for evaluating an existing codebase against agent-native architecture principles to identify parity gaps. Use when auditing for agent-native readiness, before adding a new agent capability, or when triaging agent-behavior regressions.

• plan-status

  Show a per-file checkbox progress dashboard of plans/ (open) and plans/complete/ (archived) plan documents. Use when reviewing which plans are ready to archive or checking work-in-flight at a glance.

• worktree-inventory

  List existing Git worktrees and their branch, detached, lock and prune status without changing the repository. Use when inspecting worktree locations or diagnosing isolation.

• brainstorming

  Reference guide for iterative brainstorm dialogues — question techniques, YAGNI, approach exploration, and research escalation. Use when running /flow:brainstorm or authoring brainstorm-style agents.

• compound-lifecycle

  Audit, refresh, and consolidate `docs/solutions/` to keep the institutional knowledge catalog from rotting. Use when a `docs/solutions/` sweep is needed or after `knowledge-compounder` flags an older entry as superseded.

• create-agent-skills

  Expert guidance for creating Claude Code skills and agents. Use when working with SKILL.md files, authoring new skills, creating slash commands, or designing agent workflows.

• debugging

  Find root causes systematically before fixing — trace the causal chain and form hypotheses with predictions for uncertain links. Use when debugging errors, test failures, stack traces, or when stuck after failed fix attempts. For delegating a stuck investigation to an independent Codex session, use

• git-worktree

  Git worktree management for isolated parallel development, and restacking a stack whose branches live in separate worktrees. Use when reviewing PRs in isolation, working on multiple features simultaneously, when workflows offer worktree option, or when a restack fails with already used by worktree.

• ideation

  Generate 3 grounded approaches to a soft problem, then hand the chosen one off to `brainstorm-orchestrator`. Use when the problem statement is still vague or `/flow:brainstorm` narrows too quickly.

• local-config

  Defines the yellow-plugins.local.md per-project config file schema. Use when authoring commands that should accept per-project overrides for review pipeline behavior, reviewer set narrowing, depth controls, or focus-area filtering.

• mcp-health-probe

  Canonical MCP server health classification (OFFLINE / DEGRADED / HEALTHY plus PRESENT (untested) refinement) for `/<plugin>:status` commands. Use when authoring a status command that needs to distinguish 'MCP never started' from 'MCP running but upstream API degraded'.

• mcp-integration-patterns

  Shared patterns for ruvector recall/remember and morph discovery integration (the ruvector protocol constants are a replica of yellow-ruvector's canonical memory-query skill). Use when authoring commands or agents that should leverage institutional memory and advanced editing tools.

• memory-recall-pattern

  Recall-Before-Act pattern for ruvector — query past learnings via hooks_recall at workflow start. Use when authoring commands or agents that should seed a workflow with relevant institutional memory before executing.

• memory-remember-pattern

  Tiered-Remember-After-Act pattern for ruvector — record learnings via hooks_remember at workflow completion with signal-strength tiers (Auto/Prompted/Skip). Use when authoring commands that should compound institutional memory from workflow outcomes.

• morph-discovery-pattern

  Morph discovery + fallback pattern — discover edit_file and warpgrep at runtime via ToolSearch, prefer them for large edits and intent-based search, silently fall back to Edit/Grep when yellow-morph is missing. Use when authoring agents that edit files or run semantic searches.

• multi-host-fleet

  Multi-host plugin credential and config reference for yellow-plugins. Use when setting up a new workstation, configuring CI/devcontainer, replicating credentials across a fleet, or wiring a secrets manager. Documents the canonical shell env var names for every credential-bearing plugin.

• optimize

  Run a metric-driven optimization pass: parallel candidate variants scored against an LLM-as-judge analytic rubric. Use when comparing approaches against a measurable goal — anywhere 'better' can be expressed as a per-criterion rubric. For session-level plan-adherence and scope-drift review, use /flo

• security-fencing

  Canonical prompt-injection hardening block for agents that analyze untrusted content (source code, CI logs, workflow files). Use when authoring an agent that reads untrusted input — copy the appropriate variant verbatim into the agent body; only pure output-only agents (no file reading, no untrusted

• session-handoff

  Write a validated session-handoff note at plans/handoff/<YYYY-MM-DD>-<slug>.md, or resume from an explicitly named one after a read-only preflight. Use when the user says \"create a handoff\", \"save session state\", \"handoff before compact\", \"pick up where we left off\", or names a plans/handoff

• session-history

  Search prior sessions across Claude Code, Devin, and Codex for the same problem or topic. Use when the current session cannot see prior context — after agent compaction, session boundary, or when reconstructing a multi-session decision trail. This searches raw prior-session transcripts; for distille

• stack-provider-guard

  Enforce the stacked-PR provider invariants before any provider-changing action — exactly one enabled, managed scopes fail closed, no direct settings edits, no silent fallback. Use when validating a proposed provider switch or auditing current provider state.

• stack-provider-router

  Resolve which stacked-PR provider is active and route provider-specific work to it, or refuse when the state is ambiguous. Use when a workflow needs to know whether Graphite or GitHub native stacks is in effect before running a stack operation.

Slash commands (19)

• /yellow-core:compound:review-staged

  Manually drain the compound-staging ledger ahead of the SessionStart auto-drain threshold. Use when you want to flush pending session-transcript entries to docs/solutions/ + MEMORY.md right now (e.g., before context window cycles) without waiting for count >= 5 or oldest > 48h.

• /yellow-core:flow:brainstorm

  Explore a feature or problem through iterative Q&A and optional research before planning. Produces docs/brainstorms/<date>-<topic>-brainstorm.md for /flow:plan to auto-detect.

• /yellow-core:flow:compound

  Document a recently solved problem to compound team knowledge into memory or solution docs

• /yellow-core:flow:decompose

  Decompose a spec from plans/specs/ into dependency-ordered shell files in plans/shells/, enforcing R-id coverage and depends_on traceability. Run /flow:pick-next-shell next to start implementing.

• /yellow-core:flow:expand-shell

  Expand one shell from plans/shells/ into a concrete checkbox plan in plans/, verifying Consumes against the live codebase, then deleting the shell only after approval. Run /flow:work on the resulting plan next.

• /yellow-core:flow:pick-next-shell

  Pick the lowest-numbered shell whose dependencies are archived in plans/complete/, expand it via /flow:expand-shell, capture learnings, and halt for a fresh /flow:work session. Reports deadlocks and the terminal state explicitly.

• /yellow-core:flow:plan

  Transform feature descriptions into structured implementation plans

• /yellow-core:flow:review

  Session-level review of plan adherence, cross-PR coherence, and scope drift with autonomous P1 fix loop

• /yellow-core:flow:spec

  Draft a requirements spec (stable R1..Rn IDs + design) through guided dialogue, written to plans/specs/<slug>.md as the input to /flow:decompose. Produces a spec only — no code.

• /yellow-core:flow:work

  Execute implementation plans systematically with testing and quality checks

• /yellow-core:plan:complete

  Archive a completed plan with two safety gates: Gate A scans for unchecked task boxes; Gate C verifies merged-PR evidence via file-commit provenance (with a commit-subject fallback for merge-queue PRs), then a strict slug match, then a loose token-coverage fallback. Use when a plan is fully shipped

• /yellow-core:plan:status

  Show a per-file checkbox progress dashboard of plans/ (open) and plans/complete/ (archived). Use when reviewing which plans are ready to archive or checking work-in-flight at a glance.

• /yellow-core:setup:all

  Run setup for all installed marketplace plugins. Checks local prerequisites, MCP visibility, environment variables, and plugin status, then offers interactive setup for plugins that need it.

• /yellow-core:setup:claude-web

  Prepare a repository for Claude Code Web: audit and scaffold .claude/settings.json, scripts/install_pkgs.sh bootstrap, .gitattributes, .gitignore, and .github/workflows/claude.yml. Use when first enabling cloud sessions, after adding MCP servers, or when cloud sessions fail to find expected tools.

• /yellow-core:stack:select

  Select the active stacked-PR provider (graphite or github) at user, project, or local scope — shows the exact commands first, enables one provider, disables the other, and refuses managed-scope conflicts. Use when choosing or switching stacked-PR providers.

• /yellow-core:stack:status

  Report which stacked-PR provider is active and classify the state as UNSELECTED, READY_GRAPHITE, READY_GITHUB, CONFLICT, CONFIG_MISMATCH, CONFIG_INVALID, MANAGED_CONFLICT, or PARTIAL_TOOLING. Use when checking which provider is in effect or diagnosing why a stack workflow refused to run.

• /yellow-core:statusline:setup

  Generate and install an adaptive Python statusline for yellow-plugins. Auto-detects installed plugins and their MCP servers, previews the result, and writes to ${CLAUDE_CONFIG_DIR:-~/.claude}/settings.json on confirmation; `observer enable|disable [--yes]` and `observer status` manage the opt-in con

• /yellow-core:worktree:cleanup

  Scan git worktrees, evaluate staleness, and remove stale worktrees with safeguards

• /yellow-core:worktree:restack

  Restack a stack whose branches live in separate worktrees (use when a restack fails with "already used by worktree"), then restore every worktree; pauses on conflicts and resumes with --continue or --abort

Hooks (3)

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-start.sh"

• PreCompact

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pre-compact.sh"

Similar plugins