dh_comms

Create a structured decision workflow for design-heavy repositories. Use when the user needs to compare options with tradeoff analysis, assign a decision owner, and track consequences. Produces a DW-NNN document with options, pros, cons, and tradeoff analysis.

Turn a rough design discussion into a structured written brief. Use when the user has unstructured notes, chat logs, or conversation fragments that need to become a clear document with positions, open questions, and decision points.

Synchronize documentation indices and cross-references. Use after adding, renaming, moving, or deleting documentation files. Finds orphaned docs, stale links, and broken cross-references, then fixes them and reports changes.

Collect user feedback about the Agentic Meta Project and file it. Use when the user says "feedback", "report a bug", "file an issue", or wants to report friction, suggestions, or feature requests. Files as a GitHub issue if gh CLI is available, otherwise writes a local report.

Package a locally discovered lesson for forwarding to the Agentic Meta Project. Use after a session review identifies a finding that generalizes beyond this project -- a template gap, missing skill, or structural issue that would affect any project using the system.

Create or manage a bug-fix workflow packet. Use when the user reports a bug, says "fix this bug", or needs a structured workflow for diagnosing and resolving a defect. Emphasizes reproduction, root cause analysis, minimal fix, and regression testing.

Create or manage a feature workflow packet. Use when the user wants to add new user-visible functionality and needs a tracked workflow with acceptance criteria, scope boundaries, and a verification strategy.

Initialize or refresh Project Memory for a repository. Use after amplifying a new repo, when the user says "init PM", "set up project memory", or when pm-index.md is missing or empty. Surveys the codebase, creates starter PM units, and populates the index.

Create or manage an investigation workflow packet. Use when the user needs to explore an unknown, test hypotheses, or answer a question whose output is knowledge rather than code. Structures the work around hypotheses, evidence collection, and decision-ready conclusions.

Load the smallest set of Project Memory units relevant to the current task. Use at the start of any task that needs project context. Reads pm-index.md, selects 1-3 relevant units based on task scope, and loads them into working memory without polluting context with unrelated knowledge.

Create or manage a performance workflow packet. Use when the user wants to measure, benchmark, or optimize runtime performance with measurable baselines and targets. Drives performance work to completion with evidence at every step.

Create or manage a refactor workflow packet. Use when the user wants to restructure existing code without changing user-visible behavior. Emphasizes boundary preservation, regression risk identification, and verification gates at each step.

Assess whether PM granularity and structure match current work patterns. Use after several workflows have completed, or when PM feels bloated or fragmented. Checks coverage gaps, split/merge candidates, load frequency, and transient noise. Produces a reflection report with recommendations.

Execute structural recommendations from pm-reflect's reflection report — splits, merges, removals, and coverage gap fills — with explicit user approval for each change. Use after reviewing a pm-reflect report and deciding which recommendations to act on.

Create or manage a review workflow packet. Use when the user wants a structured code, design, or document review with severity-categorized findings, file-level traceability, and verification gap identification.

Persist durable knowledge back into Project Memory after meaningful work. Use at session end or after completing a significant task. Updates affected PM units, pm-current-state.md, decisions, glossary, and code-navigation units so the next session inherits accurate project truth.

Validate Project Memory for structural correctness. Use when the user says "validate PM", when session-init flags inconsistencies, or periodically to detect PM rot. Checks for broken anchors, stale units, schema violations, orphan files, and index drift. Auto-heals index entries.

Create a normalized session capture file preserving what happened in a session. Use at the end of a work session, or when the user says "capture session" or "save session". Records session goal, work performed, decisions, blockers, and verification results to .untracked/session-captures/.

Perform the full end-of-session sequence. Use when the user says "close", "wrap up", "done for now", "session-close", or similar. Updates workflow documents, persists PM knowledge, commits changes in logical groups, runs session-capture, and delivers a summary.

Bootstrap a new agent session. Use at the start of every conversation or when the user says "start session", "init", or "begin". Reads project metadata, identifies active workflows, detects prior aborted sessions, and produces a concise briefing so the agent can begin work with minimal context loading.

Review session captures and extract process improvements. Use when the user says "review session", "session review", or when session-capture recommends a review (typically every 5 captures). Identifies failure modes, positive patterns, and drafts local proposals or forward-to-meta lessons.

Verify that all workflow and project state documents are consistent. Use when the user says "state check", "check state", or when session-init flags inconsistencies. Checks for orphan directories, dangling table entries, lifecycle mismatches, stale handoffs, and empty run-logs.

Perform the full completion sequence for a finished workflow. Use when all acceptance criteria are met and the workflow is ready to move to done state. Updates dossier, writes final run-log and handoff entries, moves the packet directory, and archives the entry in active-workflows.md.

Create a complete workflow packet from a clear work request or refined brief. Use when the user has a well-defined task ready to become a tracked workflow, or after workflow-refine produces a brief. Creates dossier, run-log, handoff, and artifacts files in draft state.

Gate check before promoting a draft workflow to active. Use after workflow-create to verify the packet is complete enough for autonomous execution. Validates dossier sections, checks for write-scope conflicts, and produces a pass/fail readiness checklist.

Turn rough user input into an autonomy-ready brief. Use when the user describes work that is vague, incomplete, or needs clarification before it can become a workflow packet. Asks clarifying questions, proposes concrete options, and produces a structured brief for workflow-create.

Resume work on an existing workflow in a new session. Use when the user says "resume", "continue", "pick up where we left off", or names a specific workflow ID to work on. Loads the handoff, dossier, and run-log, then begins executing the next step.