three-pillars

Plugin three-pillars from marketplace three-pillars in CurtisThe/three-pillars-plugin. Commands read from the repo's manifest — 17 days ago.

Skills (40)

• council

  Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.

• tp-design-audit

  Design Audit — multi-angle review of a detailed design against the actual codebase before implementation.

• tp-design-complete

  Mark a TDD design as complete — stamp completion, archive handoff.md, archive to three-pillars-docs/completed-tp-designs/, and optionally commit + open a PR merging the design branch back to the base branch.

• tp-design-detail

  Produce a detailed-design.md from an existing design.md. Maps high-level entities and behaviors to concrete modules, interfaces, and test boundaries.

• tp-design-learn

  Synthesize a completed design's impact into project docs updates and identify affected sibling designs. The "close the loop" step after implementation-audit.

• tp-design-release

  Release your lock on a design without completing it. Use when you're stepping away and want a teammate to pick it up cleanly, without them having to --force-takeover.

• tp-design

  Interactive high-level design conversation that produces a design.md artifact in three-pillars-docs/tp-designs/{name}/. First step in the TDD pipeline.

• tp-docs-init

  Scaffold architecture.md, product_roadmap.md, and known_issues.md in three-pillars-docs/ from codebase analysis. Creates the three project docs that the TDD pipeline reads for context. Assumes three-pillars-docs/vision.md already exists — if missing, recommends /tp-setup first.

• tp-docs-update

  Targeted update to vision.md, architecture.md, product_roadmap.md, and/or known_issues.md after a milestone. Shows diff-style proposals for user approval.

• tp-escalate

  Escalate a stuck design run from the seat to a Fable agent, or record feedback on a past escalation ruling. Use when the seat is unsure how to rule on a gate and needs a second opinion.

• tp-guide

  Read project docs and propose what to do next. Surfaces highest-impact work from roadmap, known issues, and in-flight designs.

• tp-implementation-audit

  Final audit of a completed plan — verify the full implementation against both design.md and detailed-design.md.

• tp-inflight

  Print the in-flight design registry — every origin/tp/* design branch with its owner, phase, branch, age, and staleness — built live from the remote. Read-only, fail-open, no lock, no side effects. Use to see what other designs are in flight before you start work.

• tp-merge-from-main

  Sync a base branch INTO a design's worktree (base-sync) and auto-resolve the safe living-doc conflict classes behind a zero-drop verifier, deferring everything semantic to the human. Re-runs tests, re-pushes only when green, updates the PR. This is the reversible base-into-branch operation — landing

• tp-merge

  Land a reviewed PR at the irreversible boundary: enforce the deterministic merge gate (require_merge_gate_pass — seven predicates incl. a current human approval, a fresh ci-local stamp, and a head-bound review-proof comment, plus the fragility_clear test-fragility predicate) and run the irreversible

• tp-migrate

  Migrate a three-pillars repo from the legacy docs/tdd-* layout to the current three-pillars-docs/tp-* layout. Wraps skills/_shared/migrate.py.

• tp-phase-implement

  Execute a phase from plan.md by running red-green-refactor cycles for each task. Spawns subagents for independent tasks within a phase.

• tp-phase-review

  Review what was built against the plan and design. Flags gaps, regressions, and deviations. Writes review.md.

• tp-plan-audit

  Plan Audit — verify plan.md is consistent with design.md and detailed-design.md. Runs deterministic scripts then convenes an engineering council for judgment calls.

• tp-plan

  Generate a plan.md from detailed-design.md — a sequenced list of implementation tasks, each with test criteria, ready for /tp-phase-implement.

• tp-post-merge
• tp-pr-fix
• tp-pr-iterate
• tp-promote
• tp-revert
• tp-run-full-design
• tp-seed
• tp-session-clear
• tp-session-restore
• tp-session-save
• tp-setup
• tp-spec
• tp-spike-auto
• tp-spike-implement
• tp-spike-learn
• tp-spike-plan
• tp-spike-results
• tp-spike
• tp-task-cycle
• tp-test-setup

Subagents (58)

• council-ada-medium

  Strata-only medium-effort copy of council-ada; spawned via strata_effort.py spawn.

• council-ada

  Council member. Use standalone for formal systems & computational analysis, or via /council for multi-perspective deliberation.

• council-aristotle-medium

  Strata-only medium-effort copy of council-aristotle; spawned via strata_effort.py spawn.

• council-aristotle

  Council member. Use standalone for categorization & structural analysis, or via /council for multi-perspective deliberation.

• council-aurelius-medium

  Strata-only medium-effort copy of council-aurelius; spawned via strata_effort.py spawn.

• council-aurelius

  Council member. Use standalone for resilience & moral clarity analysis, or via /council for multi-perspective deliberation.

• council-feynman-medium

  Strata-only medium-effort copy of council-feynman; spawned via strata_effort.py spawn.

• council-feynman

  Council member. Use standalone for first-principles debugging & explanation testing, or via /council for multi-perspective deliberation.

• council-kahneman-medium

  Strata-only medium-effort copy of council-kahneman; spawned via strata_effort.py spawn.

• council-kahneman

  Council member. Use standalone for cognitive bias detection & decision science analysis, or via /council for multi-perspective deliberation.

• council-karpathy-medium

  Strata-only medium-effort copy of council-karpathy; spawned via strata_effort.py spawn.

• council-karpathy

  Council member. Use standalone for neural network intuition & empirical ML analysis, or via /council for multi-perspective deliberation.

• council-lao-tzu-medium

  Strata-only medium-effort copy of council-lao-tzu; spawned via strata_effort.py spawn.

• council-lao-tzu

  Council member. Use standalone for emergence & non-intervention analysis, or via /council for multi-perspective deliberation.

• council-machiavelli-medium

  Strata-only medium-effort copy of council-machiavelli; spawned via strata_effort.py spawn.

• council-machiavelli

  Council member. Use standalone for power dynamics & incentive analysis, or via /council for multi-perspective deliberation.

• council-meadows-medium

  Strata-only medium-effort copy of council-meadows; spawned via strata_effort.py spawn.

• council-meadows

  Council member. Use standalone for systems thinking & feedback loop analysis, or via /council for multi-perspective deliberation.

• council-munger-medium

  Strata-only medium-effort copy of council-munger; spawned via strata_effort.py spawn.

• council-munger

  Council member. Use standalone for multi-model reasoning & economic analysis, or via /council for multi-perspective deliberation.

• council-musashi-medium

  Strata-only medium-effort copy of council-musashi; spawned via strata_effort.py spawn.

• council-musashi

  Council member. Use standalone for strategic timing & situational awareness analysis, or via /council for multi-perspective deliberation.

• council-rams-medium

  Strata-only medium-effort copy of council-rams; spawned via strata_effort.py spawn.

• council-rams

  Council member. Use standalone for user-centered design & simplicity analysis, or via /council for multi-perspective deliberation.

• council-socrates-medium

  Strata-only medium-effort copy of council-socrates; spawned via strata_effort.py spawn.

• council-socrates

  Council member. Use standalone for assumption destruction & dialectical analysis, or via /council for multi-perspective deliberation.

• council-sun-tzu-medium

  Strata-only medium-effort copy of council-sun-tzu; spawned via strata_effort.py spawn.

• council-sun-tzu

  Council member. Use standalone for adversarial strategy & competitive analysis, or via /council for multi-perspective deliberation.

• council-sutskever-medium

  Strata-only medium-effort copy of council-sutskever; spawned via strata_effort.py spawn.

• council-sutskever

  Council member. Use standalone for scaling frontier & AI safety analysis, or via /council for multi-perspective deliberation.

• council-taleb-medium

  Strata-only medium-effort copy of council-taleb; spawned via strata_effort.py spawn.

• council-taleb

  Council member. Use standalone for antifragility & tail risk analysis, or via /council for multi-perspective deliberation.

• council-torvalds-medium

  Strata-only medium-effort copy of council-torvalds; spawned via strata_effort.py spawn.

• council-torvalds

  Council member. Use standalone for pragmatic engineering & shipping analysis, or via /council for multi-perspective deliberation.

• council-watts-medium

  Strata-only medium-effort copy of council-watts; spawned via strata_effort.py spawn.

• council-watts

  Council member. Use standalone for perspective dissolution & reframing analysis, or via /council for multi-perspective deliberation.

• tp-certifier

  Guard certifier subagent. Authors RED/GREEN records that try to break each guard claim, dry-runs and repairs them, and returns a records file + sha256. Never commits and never decides status.

• tp-drafter-xhigh

  Cheap-tier drafter subagent. Writes one named output file from the inputs in its prompt, makes no other edit and no commit, and stops and reports on any block. Spawned only by the cheap-dispatch loop. (xhigh)

• tp-drafter

  Cheap-tier drafter subagent. Writes one named output file from the inputs in its prompt, makes no other edit and no commit, and stops and reports on any block. Spawned only by the cheap-dispatch loop.

• tp-explainer

  Explainer drafter subagent. In draft mode it turns one explain request bundle into one explain envelope; in check mode it checks a drafted envelope against the same bundle and writes a corrected envelope. Reads only the request bundle and the STE guide, writes one named output file, makes no commit

• tp-finalizer

  The first stop for every halt in a run. One expert subagent that diagnoses the stop, applies the real-usage blocking bar, makes structural fixes with one confirming check, and replies `resolved` or `escalate` with a written diagnosis. Never merges, force-pushes, deletes remote state, or works around

• tp-generator

  Delegated generator subagent for the autonomous orchestrator. Runs an --auto generator skill inline; in patch mode edits the existing artifact only against the findings.

• tp-impl-auditor

  Read-only implementation-audit subagent. Synthesizes audit findings or runs the single light-mode fidelity audit; never edits, writes or commits.

• tp-phase-checker

  Per-phase check judge for /tp-run-full-design Slot 7 and just-do-it runs. Reads one phase's diff, the deterministic hits and the cheap finder's reply, and delivers findings only through the phase_check.py put command.

• tp-readonly-auditor

  Read-only audit subagent for the autonomous orchestrator. Reads design + plan + codebase, may run the test suite, never edits/writes/commits.

• tp-review-confirmer-deep

  Review-angle finder for Tier 7 and tp-pr-iterate. Reads the change, reports findings, and delivers its reply only through the round_scratch.py put command. (deep)

• tp-review-confirmer-medium

  Strata-only medium-effort copy of tp-review-confirmer; spawned via strata_effort.py spawn.

• tp-review-confirmer

  Review-angle finder for Tier 7 and tp-pr-iterate. Reads the change, reports findings, and delivers its reply only through the round_scratch.py put command.

• tp-runbook

  Cheap-tier runbook subagent. Executes a mechanical, fully specified runbook step and stops and reports on any block. Inert until a dispatch site adopts it.

• tp-spawn-host

  Fixed-Sonnet spawn host. Makes exactly one Agent call with the subagent_type, model and prompt it is given, then replies done.

• tp-task-worker-local-medium

  One-task implement worker for `--local` dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line. (rung local-medium)

• tp-task-worker-local-xhigh

  One-task implement worker for `--local` dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line. (rung local-xhigh)

• tp-task-worker-opus-medium

  One-task implement worker for `--local` dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line. (rung opus-medium)

• tp-task-worker-opus-xhigh

  One-task implement worker for `--local` dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line. (rung opus-xhigh)

• tp-task-worker-sonnet-medium

  One-task implement worker for `--local` dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line. (rung sonnet-medium)

• tp-task-worker-sonnet-xhigh

  One-task implement worker for `--local` dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line. (rung sonnet-xhigh)

• tp-task-worker

  One-task implement worker for `--local` dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line.

• tp-worker

  Write-capable worker subagent for the autonomous orchestrator. Implements a plan on a candidate branch, commits, pushes, and returns the candidate.v1 envelope.

Similar plugins