anti-hall

Explain anti-hall's optional DevSwarm integration from Codex — the hivecontrol reference KB, the (designed, unbuilt) workspace-tier orchestration, and the shipped layered recovery model (Claude-side companion: child self-report → supervisor poke → escalate-to-parent, automatic path NEVER kills, plus the on-demand devswarm-recover CLI — the only kill path). Use when the user asks about DevSwarm, hivecontrol, or the anti-hall liveness supervisor while working in Codex.

Explain and activate anti-hall's optional DevSwarm integration — the hivecontrol reference KB, the (designed, unbuilt) workspace-tier orchestration, and the shipped layered recovery model (child self-report → supervisor poke → escalate-to-parent, automatic path NEVER kills) plus the on-demand devswarm-recover CLI (the only path that ever kills). Use when the user asks "explain the anti-hall DevSwarm integration", "how do I activate the DevSwarm supervisor", "what DevSwarm addons does anti-hall have", "tune the liveness supervisor", "recover a stuck DevSwarm workspace", or anything about hivecontrol / DevSwarm workspaces from an anti-hall angle.

Check or update anti-hall from the local marketplace clone. Use when the user asks to update anti-hall, check whether anti-hall is current, or refresh the Codex port files.

Update anti-hall to the latest released version and show the changelog delta. Use when the user says "update anti-hall", "/anti-hall:update", "upgrade the plugin", "is anti-hall up to date", or "check for an anti-hall update". Fast-forward-pulls the marketplace clone, mirrors the new version into the plugin cache, prints what changed, then has the user reload in-session via /reload-plugins (rarely, a harness build may require a restart — the skill says so when relevant).

Brief the agent that installs or operates anti-hall (in Codex/OMX) on how the whole system works — a DERIVED, live enumeration of every installed hook, the shipped skills, the DevSwarm coordination substrate (mechanical triggers, store, CLI, auto-safe migration), and a docs/KB map. Generated from the real hooks.json and files on disk, never a hardcoded list, so it can't drift. Use when the user asks "brief me on anti-hall", "what's in this build", "how does the whole system work", or when onboarding an agent to install/run anti-hall. For "is it actually installed in Codex / do the guards fire", use anti-hall-doctor.

Brief the agent that installs or operates anti-hall on how the whole system works — a DERIVED, live enumeration of every installed hook (grouped by event, each with its own one-line purpose), the shipped skills, the DevSwarm coordination substrate (mechanical triggers, store, CLI, auto-safe migration), and a docs/KB map. Generated from the actual hooks.json and the files on disk, never a hardcoded list, so it can't drift. Use when the user asks "brief me on anti-hall", "what's in this build", "how does the whole system work", "give me the anti-hall system overview", "what hooks/skills/substrate ship here", or when onboarding an agent to install or run anti-hall. For "is it actually working / do the guards fire", use the `doctor` skill instead.

Iterative TRIO-debate + fix-wave protocol for hardening non-trivial PRs and changes before merge. Spawns a parallel Reviewer + Auditor + Critic trio, dispatches fix waves, loops until convergence (zero NEW P0 or P1 blockers). Use before merging anything with cross-file risk, cross-PR coordination, security-sensitive changes (auth, signing, redaction, prompt-injection defense), schema migrations, production-data touches, shell scripts, CI/workflow YAML, cross-repo coordination, or LLM prompt work — anywhere a silent failure would be expensive. Born from a real project where 7 iteration rounds caught 30+ bugs that solo review would have missed.

One lean, anti-hall-native workflow for shipping any change correctly — from a one-line fix to a multi-phase feature. Scales rigor to blast radius (S/M/L tiers). Brainstorm + plan happen IN PLAN MODE (ExitPlanMode is the approval gate); the plan is hardened with the deadly-loop BEFORE any code; on large work the disjoint build phases and the per-phase deadly-loop fan out as a Workflow swarm; each phase is verified with fresh evidence and a vacuous-test guard, then hardened until zero NEW P0s or P1s. Standalone — depends only on Claude Code built-ins (plan mode, the Workflow tool) plus anti-hall's own deadly-loop and always-on guards. Use when the user says "let's build X" / "implement Y" / "fix Z" and you want it done right the first time. Replaces feature-launch.

Codex-native context and usage conservation mode. Use when the user asks for context conservative mode, limit conservation, cheap-model routing, or reducing context/token burn while keeping work moving.

Codex-native equivalent of anti-hall deadly-loop. Use to harden risky changes with repeated adversarial review and fix waves until no new P0/P1 blockers remain.

Codex-native Flutter debugging loop. Use when debugging Flutter apps, simulator/emulator behavior, UI regressions, or widget/service failures.

Codex model routing policy for anti-hall work. Use when selecting models for planning, implementation, review, debate, or mechanical execution in Codex.

Integrate anti-hall with oh-my-codex (OMX). Use when the user asks about OMX, omx setup/doctor, Codex workflows, cx.sh, dangerous bypass launch, or activating anti-hall workflows through OMX.

Codex-native orchestration discipline for multi-step or parallel work. Use when the task has several independent subtasks, needs review/verification, or risks bloating the main context.

Codex-native root-cause debugging discipline. Use when investigating a bug, failing test, broken config, or runtime behavior before proposing or applying a fix.

Codex-native ship-it workflow. Use to plan, implement, verify, and harden a change with rigor scaled to blast radius. Replaces anti-hall-feature-launch (retired 2026-07-05, matching the Claude-side ship-it/feature-launch consolidation from v0.27.0).

Behavior-preserving simplification workflow for Codex. Use when the user asks to simplify, deslop, trim fat, or reduce over-engineering.

Health-check anti-hall — confirm Node is found, every hook is present + syntax-valid, the guards actually fire (live behavioral self-tests on git-guard / command-guard / edit-guard / swarm-guard / model-routing-guard), and the statusline is installed. Use when the user asks "is anti-hall working / active / running", "check the hooks", "anti-hall doctor", "are the guards on", or after install/update to verify everything is live.

Swarm orchestration with a non-blocking main thread. Use whenever work is heavy, long-running, or parallelizable - builds, tests, deploys, data dumps, research, codebase sweeps, multi-part features, or any operation that would otherwise make the user wait. The main conversation stays a coordinator: it decomposes work, launches background and parallel subagents for anything that can run without conflict, keeps itself free to talk to the user, then collects and synthesizes results. Trigger on multi-step tasks, 2+ independent subtasks, anything expected to take more than ~30s or produce verbose output, or any time the user signals the main thread feels blocked/slow.

Idempotent Codex setup for anti-hall. Use when the user asks to activate anti-hall, set it up for Codex, or install the Codex hooks.

Register or audit deliberate technical debt markers in Codex. Use when the user asks to track debt, audit shortcuts, or list anti-hall debt markers.

Check anti-hall's Codex installation and runtime posture. Use when the user asks whether anti-hall is active in Codex, whether hooks are installed, or why a guard did or did not fire.

Explain and install anti-hall statusline support where available. Use when the user asks for the anti-hall statusline in Codex or wants OMC/anti-hall status visibility.

Inspect or integrate optional oh-my-claudecode/OMC state with anti-hall in Codex. Use when the user asks whether OMC is installed for Codex or why anti-hall did not install OMC.

Run a DOUBLE / TRIPLE / QUADRUPLE deadly loop — the deadly-loop TRIO (Sonnet 5 Reviewer + Opus Auditor + Codex Critic) multiplied N× in parallel, auditing a target (whole repo, a diff, or named files) with diversified lenses, then dedup + synthesize, optionally fix-wave and re-converge. Use when the user says "double deadly loop", "triple deadly loop", "quadruple deadly loop", "deep multi-agent review", "have multiple flagship + codex agents review everything", or wants a heavier review than the standard 1× deadly-loop. Multiplier — double=2× the trio (6 agents), triple=3× (9), quadruple=4× (12).

Install or enable the anti-hall statusline (rich line-1 statusline + phase bar) in the current repo or globally. Use when the user asks to "install the statusline", "add the bar", "enable the phase bar here", "set up the statusline in this project", or "show the statusline everywhere". Writes the statusLine entry into the correct settings file (user scope by default, project-local on request) and reminds the user to restart.

Register and audit DELIBERATE technical debt via `// anti-hall: <ceiling>,<when>` markers — a budgeted, harvestable alternative to vague TODOs. Greps the tree for markers, parses each ceiling + payback trigger, and flags rot-risk (markers with no trigger, or in code untouched past a staleness threshold). Use when the user says "track this debt", "audit our debt", "what shortcuts did we take", "show the anti-hall markers", or "is this debt rotting". NOT a license to leave work undone — see boundaries.

Harvest and apply code simplifications on recently-changed (or named) code — dead code, reinvented stdlib/builtins, premature generality, verbose patterns, and AI-slop filler — each tagged by category, with a single MEASURED `net: -N lines` score (the real post-apply diff delta, never a projected estimate). Use when the user says "simplify this", "deslop", "anti-slop", "trim the fat", "this is over-engineered", or "shrink this". Behavior-preserving by contract — verify tests before and after.

One-shot idempotent anti-hall setup. Checks statusline installation, reports model-routing state, writes a sentinel so it doesn't repeat. Use when the user says "activate anti-hall", "set up anti-hall", "run first-time setup", or "anti-hall activate". NOT auto-run — user-invoked only.

Drive a Flutter app in debug mode and close the fix loop — run with agent-controlled hot reload, drive the UI with semantic taps + agent-visible screenshots, watch runtime errors / logs / VM service, then reproduce → read error → root-cause → fix → hot reload → visually re-verify. Use when the user says "debug my Flutter app", "drive the simulator/emulator", "reproduce this bug in the app", "fix this and verify it in the UI", "hot reload and check", or wants an end-to-end Flutter debug loop. iOS fully; Android taps/screenshots VERIFIED on emulator (FP7 2026-06-11).

Evidence-driven debugging discipline. Use when investigating ANY bug, failure, crash, alert, flaky test, or unexpected behavior, before proposing or applying a fix. Enforces no-cause-no-fix - collect evidence, trace the full sequence, instrument when evidence is missing, prove the original and root cause (not the surface symptom), then fix and verify. Trigger on "why is X failing", "debug Y", "this error", "it crashes", "investigate Z", or any symptom that does not yet have a proven mechanism.