navapbc/digital-service-orchestra
Agent
Bug investigator (opus, ESCALATED Code Tracer): deep execution-path tracing, dependency-ordered analysis, state and concurrency inspection.
navapbc/digital-service-orchestra
Agent
Bug investigator (opus, ESCALATED Code Tracer): deep execution-path tracing, dependency-ordered analysis, state and concurrency inspection.
navapbc/digital-service-orchestra
Agent
Bug investigator (opus, ESCALATED Empirical Agent): authorized to add temporary logging/debugging; veto authority over theoretical consensus; must confirm artifact revert.
navapbc/digital-service-orchestra
Agent
Bug investigator (opus, ESCALATED History Analyst): deep timeline reconstruction, fault tree, commit bisection beyond ADVANCED depth.
navapbc/digital-service-orchestra
Agent
Bug investigator (opus, ESCALATED Web Researcher): error pattern analysis, dependency changelogs, upstream issue correlation; WebSearch/WebFetch authorized.
navapbc/digital-service-orchestra
Agent
Bug investigator (opus, INTERMEDIATE fallback persona): same investigation depth as intermediate when error-detective is unavailable.
navapbc/digital-service-orchestra
Agent
Bug investigator (opus, INTERMEDIATE tier): dependency-ordered reading, intermediate variable tracking, hypothesis elimination, ≥2 ranked fixes with tradeoffs.
navapbc/digital-service-orchestra
Agent
Plan and design reviewer agent. Evaluates implementation plans and design artifacts on feasibility, completeness, YAGNI, and codebase alignment before the user sees them. Dispatched by the /dso:plan-review skill. Use subagenttype "dso:plan-review" to dispatch this agent.
navapbc/digital-service-orchestra
Agent
Adversarial reviewer that audits epic Success Criteria → story Done Definition coverage and attacks preplanning story maps for cross-story blind spots, implicit assumptions, and interaction gaps across 8 taxonomy categories. Requires opus.
navapbc/digital-service-orchestra
Agent
Triages RED test writer failures with REVISE/REJECT/CONFIRM verdicts. Aligned with shared behavioral testing standard.
navapbc/digital-service-orchestra
Agent
Writes behavioral RED tests for TDD workflows, rejecting change-detector patterns.
navapbc/digital-service-orchestra
Agent
Schema correction specialist: repairs missing or invalid fields in review findings JSON without re-evaluating the diff.
navapbc/digital-service-orchestra
Agent
Post-fix scope-drift classifier for /dso:fix-bug. Reviews a completed fix against the original ticket scope to detect whether the diff introduces behavioral changes outside the ticket boundary. Emits a GATESIGNAL conforming to gate-signal-schema.md.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing serena_grep_reminder.py. From navapbc/rebar.
Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse).
Instructions file GitHub Copilot
Instructions for navapbc/rebar: The canonical agent & contributor guidance for this repo lives in AGENTS.md at the repository root. GitHub Copilot's coding agent already reads AGENTS.md natively, exactly as Codex does (see AGENTS.md's own note on this); this file exists so that other Copilot surfaces — Copilot Chat…
Instructions file CodexOpenCode
Instructions for navapbc/rebar, covering rebar — agent & contributor guide, record your work in rebar, not in scratch notes, the parallel-agent workflow, where to read (one-line pointers into docs/) and module-size policy (when editing rebar itself).
Instructions file
Instructions for navapbc/rebar, covering rebar — claude code entry point and claude code.
Skill Claude CodeCodex
A collaborative brainstorming protocol for designing new agents, skills, tools, or features. Use when the user wants to design/spec something together before building it, or invokes /rebar-brainstorm. Drives a one-question-at-a-time clarification loop, grounded in web research and subagent critique, until the design…
Skill Claude CodeCodex
A hypothesis-driven debugging protocol. Takes a problem (or list of problems) and drives each to a proven root cause via the scientific method under a strict two-phase discipline. Phase 1 (Understand) is analysis-only and moves through three separated stages, gather context into a descriptive dossier, fan out a…
Skill Claude CodeCodex
Autonomously executes a decomposed rebar epic under strict held-out TDD, landing each code change as a stacked review. Takes a rebar ticket id or alias, verifies it is executable — decomposed into children, or a childless story/task with a recorded file impact (stops otherwise) — creates a fresh worktree from…
Skill Claude CodeCodex
Principal-engineer codebase health pipeline, a deliberate pause between features to buy back optionality. Runs five phases. Discovery, a one-concern-per-subagent fan-out over code debt, smells, architectural decay, separation of concerns, spent optionality, doc gaps, oversized units, oracle strength, AI-generated-code…
MCP server Claude CodeCodexCursor +2
MCP server "rebar", hosted remotely at rebar.solutions.navateam.com, as configured in navapbc/rebar.
MCP server Claude CodeCodexCursor +2
Rebar can block work until an AI plan review passes, require signed completion verification before close, and reconcile its event-sourced ticket record with Jira across CLI, Python, and MCP. Runs locally from the nava-rebar Python package. Needs 36 environment variables to run.