infiquetra-claude-plugins

Route proposed Team Mimir profile behavior changes to target-owned Hermes dialogue.

Build a versioned Antigravity teammate delegation envelope and route it through the guarded agy wrapper.

Create durable Infiquetra implementation plans with issue, review, test, and deploy gates. Interrogates HOW work gets built, writes an agent-consumable plan artifact, records a plan saga, and routes to doc-review and /work. Triggers on "plan this", "how should we build this", "create a plan", "break this down", or a handoff issue ready for planning.

Coordinate a whole outcome as a durable DAG of leaf sagas. A level-triggered reconcile loop that dispatches the ready frontier to executors, harvests completion, and pages the operator only at gates and exceptions. The coordinator routes and never runs leaf work; status is derived on read. Thin coordinator verbs only — start, graph, advance, attend, resume, discover, handoff, attach — leaf work stays the native /resume, /work, /code-review, /qa.

Execute a settled Infiquetra plan to PR-ready, then own the round-N PR continuation loop. Restores and writes the work-thread saga (the primary writer), recommends an execution backend, runs risk-gated tests, calls /code-review programmatically and reads its envelope, gates hard on P0/P1 and stale reviews, and coordinates PR-open/review-request/merge under explicit confirmation — without owning deploy. Triggers on "build it", "work this plan", "execute the plan", "resume work on

Deep-dive one chosen Infiquetra idea into a right-sized requirements document before planning.

Run a structured Infiquetra code-quality review at the work-to-PR boundary. Reads the merge-base diff, runs a built-vs-planned audit plus judgment-selected review lenses, validates findings, writes a durable review artifact, appends to the work-thread saga, and routes — without mutating code. Triggers on "review this PR", "code review", "check my diff", "pre-PR review", or a /work hand-in before shipping.

CEO/founder-mode scope and ambition review. Rethink the problem, find the 10x product, challenge premises, expand or cut scope deliberately — across four committed modes (SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION). Fires upstream of execution on a /plan artifact, STRATEGY.md, /brainstorm output, or an ad-hoc scope question; produces a scope decision and routes deep rigor back to /doc-review and /code-review in a closed loop. Triggers on "think bigger", "expand scope", "is this ambitious enough", "rethink this", "scope review", or a /ceo-review invocation. Does not implement, record strategy, file issues, or change code.

Generate and critically evaluate grounded Infiquetra product, architecture, or workflow ideas. Multi-agent divergent→convergent engine — generate many, critique all, explain survivors only. Triggers on "ideate on X", "give me ideas", "what should I improve", "surprise me", "what would you change".

The Infiquetra systematic-debugging engine. Find the ROOT CAUSE of a bug, test failure, error, or unexpected behavior BEFORE any fix — trace the full trigger→symptom causal chain with no gaps, ground every hypothesis in observed evidence, and only then apply a GATED, trivial-scope, self-verified fix. Diagnosis is the primary deliverable: it writes an agent-consumable DEBUG REPORT, routes real implementation work to /work via a /handoff issue, design problems to /brainstorm, and trackable defects to /handoff. READ-ONLY on the world and the saga; never commits, pushes, opens a PR, or deploys. Triggers on "investigate", "debug this", "why is this failing", "trace this error", "root cause", a pasted stack trace / error message / issue ref, or a /qa or /loop hand-in for a deep failure.

The Infiquetra lifecycle router and resume substrate. Three modes — Route (dispatch the one next command), Drive (walk phases across the lifecycle, pausing at every gate and handoff), and Resume (scan the saga, restore the work-thread, re-enter where it left off). Reads the saga at entry, ticks it on every routing decision, and routes to the destination command — which owns its own phase work, gates, AND its own execution backend. Triggers on "loop", "where does this go", "route this", "drive it through the lifecycle", "resume", "what's in flight", an issue/plan path, or a bare ad-hoc ask.

Two-phase structured plan execution with reviewer consensus, validator gates, and guarded nonprod automation for Infiquetra repositories. Phase A runs during planning: inspect the requested work, derive workers, reviewers, and selected validators, then embed the team plan into the user-approved plan artifact. Phase B runs after approval: workers complete changes, reviewers reach consensus, scanners run, PR/CI/nonprod coordination happens only after gates pass, and testers plus monitors validate the deployed nonprod result.

One strict, bounded, read-only cross-source audit of the fleet substrate — reconciles Git worktrees, outcome registries, broker leases/fences, chain-verified run facts, outcome dispatch events, and the delegation audit store into leaked-resource / unledgered-spawn / receiptless-delegation findings plus explicit evidence errors. Absence, corruption, and incompleteness are three different verdicts; a capped or corrupt scan exits 2 and can never return clean. Reports and routes to owners; never repairs, settles, retries, releases, or reaps. Triggers on "fleet doctor", "audit the fleet", "any leaked worktrees or unledgered spawns", "/fleet-doctor".

Operator-facing GraphQL + REST helpers for the active project boards. Wraps the GitHub APIs the orchestrator uses, so Jeff can do per-card work (set Initiative/Objective fields, link or unlink sub-issues, validate card bodies, self-heal labels, discover project mappings, assign covered issues to Team Mimir) without writing GraphQL by hand. Each command is idempotent where possible, and surfaces partial failures clearly.

Create and manage SDLC issues in Infiquetra GitHub repositories using the 5-type issue taxonomy: capability, enhancement, defect, exploration, and context-update. Handles issue type selection, template-guided creation, Hermes label application, project board assignment, and milestone linking.

Live fleet telemetry — board state, agent/run state, run-fact ledger facts, and outcome economics rendered from real signals in one read-only surface. Strictly derive-on-read (no committed status field, no writes anywhere); every panel is tri-state ok / no-data / unavailable so an empty or unreadable source is labeled explicitly, never presented as a silent zero. Cites numbers and lets the operator judge — no hardcoded thresholds, not a gate, no experiment loop (that is /optimize). Triggers on "what is the fleet doing", "live telemetry", "pulse", "show run state and spend", "/pulse".

The Infiquetra lifecycle META-IMPROVEMENT ENGINE. The TERMINAL, ADVISORY lifecycle phase downstream of /qa — it reads the work that shipped, gathers evidence (git forensics behind a stale-base/wrong-today BLOCK guard, saga trajectory, gh issues/PRs READ-ONLY, session transcripts), interviews the operator, writes a concise agent-consumable retro doc, PROMOTES generalizable findings into the engineering journal (pure-append, auto), CURATES the journal + auto-memory (staleness / contradiction / dedup / rule-enforcement sweeps, propose-diff-and-wait), MARKS the select cross-repo learnings transcendent for the promote layer (single-repo, propose-diff-and-wait), and runs net-new meta-improvement passes (new-skill detection, refine the lifecycle SKILLs, refine directives, prune memory) — every one gated. It never blocks /loop, never mutates the world, never writes the saga, and never self-applies a non-journal edit. Triggers on "retro", "retrospective", "what did we learn", "leave the system smarter", a /qa or /hand

Reconcile the durable delegation audit store against claimed dispositions, flagging any delegation that claims real external-engine execution but has no receipt proving it ran. Read-only, advisory, on-demand — never a gate, never a background job. Triggers on "/delegation-audit", "did this delegation actually run", "audit delegations", "check for fallback no-ops", or a post-incident question about whether an agy/codex run was real.

Run a risk-driven Infiquetra acceptance-evidence QA gate on shipped work. Restores the work-thread saga, classifies the change into risk classes, runs acceptance checks (including browser behavior via the installed MCP), gathers evidence, assigns severity, derives a ship verdict, writes a durable QA artifact, advances the saga qa-track on pass, and routes by merge state — without fixing, committing, or deploying. Triggers on "qa", "run QA", "does this actually work", "acceptance check", "ship-readiness", or a /work or /code-review hand-in after merge.

Infiquetra deployment state and tag-promotion guidance. Use for /deploy, /deploy-status, /deploy-notes, /deploy-hotfix, rollback planning, hotfix promotion, and deployment evidence.

Route durable Infiquetra lifecycle artifacts into mission-control prepared issue drafts.

Build a versioned codex delegation envelope and route it through the guarded codex wrapper.

Review Infiquetra plans, requirements, and SDLC documents for implementation readiness.

Manage GitHub labels and project field options for Infiquetra repositories. Handles applying SDLC labels to issues, auditing repos for missing labels, deploying the full label taxonomy, auto-labeling issues based on title/body patterns, and creating new field options when new initiatives or objectives are introduced.

Manage GitHub Milestones for Infiquetra Objectives. Creates, lists, links, and tracks milestone progress when an Objective needs due-date rollup across one or more repos.

Track and drive SDLC rollout across Infiquetra organization repositories. Provides rollout status dashboards, gap analysis per repo, label and template deployment, and progress tracking. Uses GitHub repos, issue templates, labels, project mapping, and rollout-status tracking.

Manage UniFi network infrastructure — devices, clients, VLANs, firewall rules, traffic routes, port forwards, VPN, DNS, DHCP, and stats — via the UniFi OS API

Manage UniFi Protect cameras, PTZ control, motion/smart events, NVR info, liveviews, lights, sensors, chimes, and viewers

The Infiquetra lifecycle's HEAVY forensic reconstruction engine — the deep half beside /loop's lightweight restore. Two tiers — Tier 1 reconstructs from the saga's WHOLE tick-chain trajectory (not just the last frame) plus PR archaeology and explicit conflict reconciliation; Tier 2 (fallback only, no saga AND no resolvable issue) is a slim Claude-only port of CE session forensics over local JSONL logs. Read-only on the world; it writes one git-ignored re-entry tick that reuses the restored saga_id, then routes. Triggers on "resume", "reconstruct what happened", "what was tried across these PRs", a corrupt or missing local cache, or same-machine work that never wrote a saga.

Manage the Infiquetra GitHub Projects active boards: Operations, Asgard, and CAMPPS. Handles board views, status moves, item adds, terminal-item archive, WIP analysis, field discovery, and standup preparation.

Flow metrics and analysis for Infiquetra project boards using GitHub timeline events. Provides cycle time, throughput, WIP age, per-status time breakdowns, and interpretation guidance across Operations, Asgard, and CAMPPS.

Run a metric-driven Infiquetra optimization loop — define a measurable goal, baseline current behavior, generate a hypothesis backlog, run bounded one-variable experiments, measure each against hard degenerate gates before any LLM-judge, keep the best real improvement and revert the rest, and converge on the measurably-best version. Eight metric classes (perf, cost, reliability, agent-usability, security, quality/accuracy, developer-experience, maintainability). Off-chain and saga-untouched; it finds the winner, then routes it to /work to ship — it never commits, merges, or deploys. Triggers on "optimize this", "make it faster/cheaper", "tune this", "baseline and improve", "drive this metric to a target", or a perf finding handed in from /qa or /loop.

Stand up a new infiquetra agent-team repo end-to-end — context-library-compliant repo + Discord identity + GitHub identity + split-vault wiring + Ansible deploy harness — by composing a deterministic generator with two human-in-loop portal gates

Promote the select few cross-repo "transcendent" learnings into infiquetra-context-library's engineering journal as distilled, pull-only org standards. A manual, gated, agent-judged workspace pass — it enumerates every repo journal (mirroring /ideate's cross-repo grounding), reads the declared **Transcendent.** markers plus the legacy **Generalizable rule.** lines, excludes context-library (self-feed guard), clusters the same lesson across >=2 repos by judgment, distills Rule + Mechanism, and upserts ONE entry per lesson behind a propose-diff-and-wait gate keyed on a drift-stable source-key ledger. READ-ONLY on the SDLC; writes ONLY to context-library; never writes back to source repos. Triggers on "promote learnings", "run the transcendent-learnings pass", "globalize this lesson", "promote".

Interrogate a vague ask into a precise, backlog-ready WHAT spec — five-Why, scope/MVP lock, failure-mode enumeration, read-code-first, quantify-everything. Convergent and relentless on one decided direction. Triggers on "spec this out", "turn this into a spec", "what exactly are we building", "sharpen this ask before handoff", and when /office-hours, /loop, or /brainstorm have settled the WHY but the WHAT is still fuzzy.

Create or maintain the repository root STRATEGY.md — the durable direction anchor (target problem, approach, who it's for, key metrics, tracks). Interview-driven and rerunnable. Triggers on "write our strategy", "update the direction", "what are we working on", "set up the strategy doc", and when /ideate, /brainstorm, or /plan need upstream grounding and no STRATEGY.md exists yet.

The two-mode frame-finding front door for early Infiquetra thinking. Startup mode runs the six market/customer forcing questions (stage-aware); Builder mode runs discovery/shaping for infra, workflow, and internal-tooling. Finds the right frame, then routes — to /ideate, /brainstorm, /plan, or /strategy. Triggers on "office hours", "is this worth building", "help me think through this", "I have an idea but I'm not sure what it even is", "what's even the right frame here".

Application security audit focused on URL and input trust boundaries, SSRF-style risks, redirects, metadata endpoints, allowlists, and evidence-backed findings.

Operator-facing guide for the redis-channel Claude Code channel plugin. Use when the user wants to connect a Claude Code session to an external router over Redis Streams, list registered sessions, change endpoints, or troubleshoot the bridge.

Pre-deployment validation for Ansible changes targeting the Proxmox home-lab cluster — catches common mistakes before they become fix commits