conexus

Plugin conexus from marketplace nexus-plugins in Hellblazer/nexus. Commands read from the repo's manifest — yesterday.

Skills (40)

• analyze

  Use when synthesising across prose and code corpora or ranking candidates by a criterion — tries the analyze plan library first (search → reference-chain traversal → rank → generate), inline-plans on a miss.

• architecture

  Use when complex features need architectural design before implementation, or when system design decisions span multiple modules

• asks

  Use when the user asks to go through, work through or answer the asks waiting on them, or to relay answers to the sessions that raised them (RDR-245 structured asks on the threads board)

• brainstorming-gate

  Use when about to implement any feature, build any component, or make any behavioral change — requires design exploration and user approval before implementation

• catalog

  Use when working with catalog entries, resolving tumblers, creating links, understanding what's linked to a file, or seeding link context for the auto-linker. Covers resolve, link, context, and seed operations.

• cli-controller

  Use when controlling interactive CLI applications, debugging with pdb/gdb/jshell, spawning Claude Code instances, or working with REPLs and long-running processes

• codebase-analysis

  Use when exploring an unfamiliar codebase, onboarding to a project, or needing to understand module structure before making changes

• composition-probe

  Use when a coordinator bead's inter-bead composition needs verification before downstream beads begin

• decision-drift-review

  Use when critiquing a change set against decision history to check it hasn't drifted from what an RDR decided — not for routine code review, that's the `code-review-expert` agent.

• deep-analysis

  Use when surface-level analysis is insufficient and problems require hypothesis-driven investigation across multiple system components

• design-to-code-trace

  Use when doing design / architecture / planning work that walks from prose (RDRs, docs, knowledge) into the modules implementing a concept — not for open-ended topic research, that's /conexus:research-synthesis

• document

  Use when authoring or auditing documentation against existing coverage — tries the document plan library first (search prose/code → documentation-for traversal → compare), inline-plans on a miss.

• enrich-plan

  Use when beads need enrichment with execution context — file paths, code patterns, constraints, test commands.

• finishing-branch

  Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

• git-worktrees

  Use when starting feature work that needs isolation from current workspace, before executing implementation plans, or when MORE THAN ONE SESSION is working on one checkout - creates isolated git worktrees with smart directory selection and safety verification

• knowledge-tidying

  Use when validated findings need to be consolidated in the T3 knowledge store.

• mailbox

  Use when sending or draining a mailbox tuple-space message between agents or instances, or when authoring or reviewing code against the mailbox/ADDRESS template

• nexus

  Use when running nx commands for search, memory, knowledge storage, or indexing — or when unsure which nx subcommand to use

• orchestration

  Use when unsure which agent or skill fits a task, or when dispatching and gating agents (briefs, review gate, debugger escalation, pipelines)

• peer-messaging

  Use when sending to, waiting on, or answering another Claude session or dispatched agent, when a message from one arrives, or when two sessions on one machine need the same checkout, build, or test capacity

• phase-review-gate

  Use when a phase boundary is being closed — cross-walk RDR §Approach against closing beads to catch silent scope reduction before it is discovered mid-implementation

• plan-first

  Use when starting a retrieval task whose answer must be reduced from many documents — routes through nx_answer, which matches the plan library first and inline-plans on a miss. Raw search/query covers file:line or single-fact lookups, in seconds.

• plan-validation

  Use when a plan needs validation before implementation — catches gaps and codebase misalignment.

• rdr-accept-checklist

  Use when a gated RDR returned PASSED and you want to officially accept it for implementation

• rdr-audit-checklist

  Use when auditing a project's RDR lifecycle for silent-scope-reduction frequency, or when inspecting or managing scheduled periodic audits

• rdr-close

  Use when an RDR is done — close it with optional post-mortem, bead status gate, and T3 archival

• rdr-create

  Use when starting a new research-design-review document to think through a technical decision

• rdr-fix-checklist

  Use when a gated RDR has findings to fix — prints the findings with their sites, the diff since the gated commit, the pre-edit research title, and the fix rules

• rdr-gate-checklist

  Use when an RDR appears complete and needs finalization validation — structural, assumption, and AI critique checks

• rdr-research

  Use when adding, tracking, or verifying structured research findings for an active RDR

• rdr-show

  Use when needing detailed information about a specific RDR including content, research findings, and linked beads

• receiving-review

  Use when receiving any code review feedback, before implementing any suggestion - requires technical rigor and verification, not performative agreement or blind implementation

• research-synthesis

  Use when researching unfamiliar topics, comparing technology approaches, or building comprehensive understanding from multiple sources

• serena-code-nav

  Use when navigating code by symbol — finding definitions, all callers, type hierarchies, renaming safely, or editing a method body without reading the whole file. Use instead of Grep for any symbol-level task.

• strategic-planning

  Use when facing multi-step development work that needs decomposition into tasks, before writing any implementation code

• substantive-critique

  Use when architectural decisions, implementations, or documentation need deep constructive critique against specs or evidence

• tumbler-footnotes

  Use when a markdown file cites the catalog as `[label](nx://catalog/TUMBLER)` links and needs those converted to footnotes that GitHub/GitLab/VS Code actually render, or checked/reversed — drives nx catalog footnotes.

• upgrade

  Use when a user wants to upgrade nexus, migrate an existing store onto the service stack, asks what upgrade steps their install needs, is blocked on a migration, or is holding an old/dormant install that may carry era debt

• why-was-this-written

  Use when the design intent behind a failing code path must be reduced from several RDRs/notes before trusting a fix — not for dispatching a debugger, that's the debugger agent.

• writing-nx-skills

  Use when creating new conexus plugin skills, editing existing skills, verifying skill quality before committing, or promoting a memory file into a skill, script or hook

Slash commands (18)

• /conexus:analyze-code

  Analyze codebase using codebase-deep-analyzer agent

• /conexus:continuation

  Write a handoff document under /tmp capturing session state, branch, beads, T2 entries, and next-step pointers. Chat response is `cat PATH`; user copies it and pastes after /clear to bootstrap the next session.

• /conexus:create-plan

  Create implementation plan using strategic-planner agent

• /conexus:debug

  Debug test failures using debugger agent

• /conexus:devonthink-index

  Index DEVONthink records into the T3 knowledge store through nx dt index, with catalog identity on the x-devonthink-item URI and a page-coverage check

• /conexus:implement

  Implement feature using developer agent

• /conexus:nx-preflight

  Check that all conexus plugin dependencies are correctly installed and configured

• /conexus:pdf-process

  Index PDF files into the T3 knowledge store for semantic search

• /conexus:plan-audit

  Audit a plan using mcp__plugin_conexus_nexus__nx_plan_audit (RDR-080)

• /conexus:rdr-accept

  Accept a gated RDR — verifies gate PASSED in T2, updates status to accepted

• /conexus:rdr-audit

  Audit a project's RDR lifecycle for silent-scope-reduction base rate, or inspect/manage scheduled periodic audits

• /conexus:rdr-fix

  Fix an RDR's gate findings — prints the findings with their sites, the diff since the gated commit, the pre-edit research title, and the fix rules

• /conexus:rdr-gate

  Run finalization gate on an RDR — structural, assumption audit, and AI critique

• /conexus:rdr-list

  List all RDRs with status, type, and priority

• /conexus:research

  Research topic using deep-research-synthesizer agent

• /conexus:review-code

  Review code changes using code-review-expert agent

• /conexus:setup

  Set up Nexus on this machine. Shows what is missing, asks, then installs the CLI and a service in the background.

• /conexus:test-validate

  Validate tests using test-validator agent

Subagents (10)

• architect-planner

  Designs comprehensive software architecture and creates phased execution plans for complex projects. Use when starting new features requiring architectural design or planning multi-phase implementations.

• code-review-expert

  Reviews code for quality, security, and best practices. Use proactively after completing features or immediately after writing significant code changes. Brief it with a "Ship when ..." line stating the acceptance bar, and dispatch substantive-critic alongside it.

• codebase-deep-analyzer

  Performs comprehensive codebase analysis including architecture patterns, dependencies, and technical debt. Use when onboarding to projects, before major refactoring, or for system-wide understanding.

• debugger

  Systematically investigates bugs, test failures, and performance issues using hypothesis-driven debugging. Use when encountering bugs after 2-3 failed fix attempts or facing non-deterministic failures.

• deep-analyst

  Provides thorough analysis of complex problems and intricate system relationships. Use when investigating performance mysteries, debugging multi-component interactions, or understanding system behavior.

• deep-research-synthesizer

  Conducts comprehensive research across the conexus knowledge store, memory, web resources, and code repositories. Use when needing multi-source research synthesis or building comprehensive understanding of new technologies.

• developer

  Executes development tasks using test-first methodology including feature implementation and refactoring. Use proactively for implementing features from specifications or executing architectural plans.

• strategic-planner

  Creates phased TDD-driven implementation plans and decomposes complex work into tracked beads. Use for multi-phase feature planning, dependency management, breaking vague requirements into executable tasks, or iterating on existing plans.

• substantive-critic

  Provides deep constructive critique of code, documentation, plans, and designs. Identifies structural flaws, logical inconsistencies, and unvalidated assumptions. Use when reviewing architectural decisions, validating implementations against specifications, or auditing plans before committing. Brief

• test-validator

  Verifies test coverage, runs test suites, and validates test quality for code changes. Use after implementation, before marking work complete, or when test failures need systematic root-cause analysis.

MCP servers (3)

• sequential-thinking

  runs: uv tool run --directory ${CLAUDE_PLUGIN_ROOT} --no-config --quiet --python >=3.12 python ${CLAUDE_PLUGIN_ROOT}/mcp/sequential_thinking.py

• nexus

  runs: uv tool run --directory ${CLAUDE_PLUGIN_ROOT} --no-config --quiet --python >=3.12 python ${CLAUDE_PLUGIN_ROOT}/launch/nx_launch.py nx-mcp

• nexus-catalog

  runs: uv tool run --directory ${CLAUDE_PLUGIN_ROOT} --no-config --quiet --python >=3.12 python ${CLAUDE_PLUGIN_ROOT}/launch/nx_launch.py nx-mcp-catalog

Hooks (22)

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionStart

  uv

• SessionEnd

  uv

• SubagentStart
• SubagentStop

  uv

• PreToolUse

  uv

• PreToolUse

  uv

• PreToolUse

  uv

• PreToolUse

  uv

• PermissionRequest

  uv

• UserPromptSubmit

  uv

• PreCompact

  uv

• PostCompact

  uv

• Stop

  uv