infiquetra/saga

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

Run the pre-merge code review as a policy-free executor of the lifecycle repository's lens roster. Reads the lens declaration from the run record, resolves review_roster.v1 with the sdlc's own generator, runs one Lens Reviewer per selected lens, computes the verdict in code from the catalogue's strictness ladder, writes review_result.v2 into the run record, and publishes findings as exactly one pull-request comment — never an approving review. Triggers on "review this PR", "code review", "check my diff", or a /work hand-in before shipping.

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

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 mission-control issue, design problems to /brainstorm, and trackable defects to mission-control. 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 hand-in for a deep failure.

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".

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.

Run the lifecycle's functional test — the prescribed strategy catalogue. Reads the repository profile and the run record, computes the required strategies from file patterns, lets one advisory judgment widen that set and never narrow it, runs each strategy's driver to passed, failed, or blocked, appends one evidence envelope each to the run record, counts the verdict, publishes the per-strategy statuses, and routes. It never fixes anything. Triggers on "qa", "functional test", "does the shipped thing work", "run the strategies", or the release step's hand-off after a non-production deployment.

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 the chain it follows, 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 hand-in, or the end of a meaningful work loop / PR / deploy.

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 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.

Run the build loop for a settled Infiquetra plan. One worktree and branch per unit, implement, then run the written exit criterion from the run record — the mechanical baseline, the plan's functional checks, the branch preview where the repository declares one, and the scenario smoke — repeating until green, and hand the exact revision to /code-review. Restores and writes the work-thread saga (the primary writer). Triggers on "build it", "work this plan", "execute the plan", "resume work on