yellow-plugins

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 /codex:rescue.

Standard pattern for querying ruvector institutional memory before acting. Use when authoring new agents or commands that should query past patterns, findings, or solutions before executing.

Shared conventions for CI analysis — validation rules, failure patterns, error catalog, and security patterns. Use when agents or commands need CI-specific validation or pattern matching reference.

CI debugging workflow guide for self-hosted runners. Use when learning CI debugging workflows, understanding failure patterns (F01-F12), or troubleshooting GitHub Actions on self-hosted runners.

Canonical conventions for shelling out to the OpenAI Codex CLI. Use when authoring or modifying commands or agents that invoke codex exec — choosing flags, sandbox and approval modes, and parsing its output.

Canonical conventions for running batch workflows through the Composio MCP server. Use when authoring or modifying commands or agents that call Composio tools — the Workbench sandbox, Multi-Execute batching, and the local usage counter.

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.

Shared documentation conventions — templates, diagram type selection, staleness detection, severity classification. Use when agents need doc generation or audit context.

Reference conventions for how yellow-research derives slugs, formats reports, and saves output under docs/research/. Use when authoring or modifying yellow-research commands or agents that write research output.

Shared conventions for Semgrep integration — triage state mappings, API patterns, fix strategy decision tree, rate limits, and security rules. Use when commands or agents need Semgrep-specific validation, error handling, or API reference.

Internal reference for PR review workflow patterns. Use when agents or commands need shared conventions for adaptive selection, output format, or error handling.

Canonical reference for yellow-council CLI invocation, redaction, and output-parsing conventions. Use when authoring or modifying gemini-reviewer, opencode-reviewer, or the /council command.

Write a session-handoff artifact at plans/handoff/<YYYY-MM-DD>-<slug>.md capturing current task, workflow status, active artifact, open decisions, in-flight changes, and next action so a fresh session can resume without re-deriving context. Use when the user says "create a handoff", "save session state", "handoff before compact", "pick up where we left off next time", or a session is approaching a context/compaction boundary mid-task. Not the shell halt pattern — /workflows:pick-next-shell halts by design after writing its expansion artifact and needs no handoff; use this for free-form session state only.

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.

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.

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.

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.

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 /workflows:review instead.

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 input) are exempt.

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 distilled learnings, use ruvector recall (/ruvector:memory).

Canonical reference for how mempalace commands and agents integrate with the MemPalace MCP server. Use when authoring or maintaining a mempalace command or agent — exact tool naming, palace vocabulary, and error-handling rules live here.

Use when an agent needs official library docs, API examples, or migration guides. Canonical fallback chain: context7 → EXA → WebSearch. Preloaded by within-plugin agents; inlined verbatim by cross-plugin consumers.

Testing conventions and configuration reference. Use when agents or commands need config schema, severity classification, report templates, or credential rules for browser testing.

Linear workflow patterns and conventions reference. Use when commands or agents need Linear workflow context, issue writing guidance, or branch naming conventions.

ruvector workflow patterns and conventions reference. Use when commands or agents need ruvector context, MCP tool naming, current tool schemas, or error handling patterns.

Internal reference for the bottom-up Graphite stack-traversal procedure shared by /review:all and /review:resolve-stack. Use when a yellow-review command needs to walk a Graphite stack PR by PR in dependency order.

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.

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.

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.

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 `/workflows:brainstorm` narrows too quickly.

Technical debt scoring framework and scanner patterns. Use when scanner agents need scoring rubrics, category definitions, safety rules, or output schemas.

The Palace Protocol for interacting with MemPalace — wake-up sequence, query-before-assert pattern, memory stack usage, and when to use search vs KG vs navigation. Use when agents need guidance on how to interact with the palace correctly.

Git worktree management for isolated parallel development. Use when reviewing PRs in isolation, working on multiple features simultaneously, or when workflows offer worktree option.

Skill fixture used to validate the skill-reference resolver in lint-plugins.sh.

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'.

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.

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.

Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.

Document a recently solved problem to compound your team's knowledge

Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.