build-loop

Plugin build-loop from marketplace rosslabs-ai-toolkit in tyroneross/RossLabs-AI-Toolkit. Commands read from the repo's manifest — 2 days ago.

Skills (60)

• source-command-promote-experiment

  Promote an auto-promoted experimental skill or agent from project-local `.build-loop/skills/active/` into the build-loop plugin repo, making it available across every project. Requires user confirmation and opens a PR on the plugin repo for review.

• build-loop:debugging-debug-loop

  [ARCHIVED v0.1.0 — superseded by build-loop:debug-loop] Older source-tracked copy of the iterative debug loop, retained for version history. Not active and referenced by nothing; use build-loop:debug-loop.

• build-loop

  The single Build Loop plugin entrypoint. Use when the user asks to run Build Loop or requests multi-step features, fixes, refactors, migrations, schema/API changes, debugging, optimization, research, repository maintenance, or closeout. Routes plain-language intent automatically without mode selecti

• build-loop:acp-practice

  Route, build, and verify Agent Client Protocol (ACP) clients and adapters that drive coding agents over JSON-RPC stdio. Use when choosing ACP vs a PTY for an agent, or a diff touches ACP code (paths or identifiers matching acp, agent-client-protocol, session/prompt). NOT for MCP servers (use mcp-bui

• agent-rally-point

  Use when coordinating build-loop with peer coding agents, checking Rally Point presence/inbox state, posting handoffs or feedback, validating the embedded Rally Point boundary, or changing the future agent-rally-point spin-out surface.

• agent-rally-watcher

  Use when listening for Rally Point changes, wiring coordination watchers, debugging watch-loop behavior, or changing the future agent-rally-watcher spin-out surface.

• api-registry-bridge

  Use when Phase 1 Assess or Phase 5 Iterate detects a new API dependency, API config fails, or the user asks to "register this API" or "check the API registry". Consults api-registry plugin; degrades gracefully if plugin is absent. NOT for PRD strategic grounding (use `prd-bridge`) or UI verification

• build-loop:architecture-dead

  Find code/components with zero remaining callers — dead, unreachable, or orphaned files to delete. Use when the user asks to "find dead code", "clean up unused files", or "scan for orphaned components". Not for code that's still called but breaks a layer boundary or forms a cycle (use `architecture-

• build-loop:architecture-impact

  Blast-radius analysis — trace upstream/downstream dependencies for one component or file before changing it. Use when the user asks "what does changing X break" or before a cross-layer fix.

• build-loop:architecture-review

  Full architectural integrity pass — system flow, connections, documentation drift, and lessons in one report. Use when the user asks for "an architectural review" or "full integrity check" on a build crossing 2+ layers. Not for a single violation/orphan pass (use `architecture-rules`) — this is the

• build-loop:architecture-rules

  Detect structural rule violations — layer violations, circular dependencies, and connection hotspots. Use when the user asks to "check for violations" or "find circular deps". Not for code with zero callers (use `architecture-dead`) or a full narrative review (use `architecture-review`).

• build-loop:architecture-scan

  Refresh build-loop's native component/connection data before any other architecture check runs. Use when the user asks for "an architecture scan" or Phase 1 Assess finds the data stale. Not for finding violations or dead code — `architecture-rules`/`architecture-dead` need this data first.

• build-loop:architecture-trace

  Follow one component's connections end-to-end, input to output. Use when the user asks to "trace data flow", "follow this request end-to-end", or "show how X reaches Y".

• attribution-standard

  Apply the canonical four-layer Apache-2.0 attribution model (NOTICE, per-file SPDX, REUSE.toml, canary markers) to a repo. Triggers on 'stamp attribution', 'add NOTICE', 'license headers', 'attribution layers', a newly public repo, or a repo with .git but no NOTICE / no REUSE.toml / no CONTRIBUTING.

• authentication

  Use when wiring auth to a new project, debugging login errors (redirect_uri_mismatch, invalid_grant, session callback, refresh_token), or adding social/magic link flows. Covers Better Auth (Drizzle/Neon), Supabase Auth (SSR), Google OAuth, and Resend transactional email.

• auto-decision-capture

  Passively capture a substantive decision the user just made, in real time, into build-loop-memory. Fires automatically when the user confirms a choice or states a constraint — not user-invoked. Not for findings/issues (use `auto-finding-capture`), after-the-fact review (use `recursive-retrospective`

• auto-finding-capture

  Passively capture a concrete, severity-labeled finding or issue into the backlog, in real time. Fires automatically whenever an agent, audit, or critic surfaces one — never gated behind a user selection. Not for decisions (use `auto-decision-capture`) or for a judgement call the agent made without a

• building-with-deepagents

  Build or refactor an agent using the OSS `deepagents` framework (SubAgent API, middleware, tool scoping, streaming, checkpointing). Use when the user wants a multi-agent/subagent system built with deepagents, or the code imports it. Not for `.claude/agents/*.md` definitions.

• build-loop:capabilities

  Invoked by Phase 1 Assess to populate `state.json.activeCapabilities[<phase>]` with ≤8 relevant entries via plugin-surface collapse + trigger-aware demotion. Keeps the orchestrator below the empirical tool-selection ceiling. Not user-callable; orchestrator-internal.

• claim-scope

  Name the LAYER a claim lives at (working tree / repository / deployed / live behavior) and check that your instrument can reach it, before stating any fact about a system. Triggers on assertion words (is / never / only / verified / cannot) and on 'does X exist', 'did X ship'. Not for grading evidenc

• color-engine

  Use when choosing or fixing accessible colors for UI, charts, diagrams, documents, or artifacts. NOT for choosing layout, typography, or component structure. Generate color systems and verify contrast, including dark themes and accent colors.

• cost-rca

  Quantify what a context/caching/model change did to token spend and dollars, from measured usage data, never estimates. Use when the user asks "how much did that cost", "did caching save money", "why did my bill spike", or "token delta". Not for choosing which model to use (use `model-tiering`) or c

• build-loop:data-plane-worktrees

  Decide how a build/worktree safely isolates mutable non-Git state (databases, caches, volumes, indexes) so parallel work doesn't collide. Use when the user asks \"is it safe to run this in parallel\" or \"will this migration collide with the other branch\", or a run touches a database/cache/volume.

• build-loop:database-practice

  Measure a database before changing it, and prove an object is dead before retiring it. Use when a build creates or alters a table, column, or index; when a query is slow or the user asks why the database is slow; or when someone proposes dropping an empty table. NOT for worktree or data-plane isolat

• daydream

  Discover source-linked recurring coding friction and successful patterns; mine selected local sessions by host, model and effort; draft improvements and feed observational evidence to Benchmark Lab. Use through Build Loop when asked to daydream, mine reusable patterns, or learn from coding history.

• debug-loop

  Iteratively investigate and fix a live, currently-broken bug. Use when a fix didn't hold, `/build-loop:debug` is invoked, or the user wants it debugged right now. Not for checking whether this bug happened before (use `debugging-memory` first) or a post-fix blameless analysis (use `root-cause-analys

• debugging-memory

  Search Build Loop's native debugging memory before you investigate a bug, then store the verified fix afterward. Use when the user reports a crash, error, regression, or broken behavior — check what already failed this way before re-deriving it. Not for implementing the fix itself; use debug-loop.

• decision-queue

  Turn pending decisions — Operations Center tasks with status needs_input, a backlog of open questions, anything blocked on the user's judgment — into one interactive page the user answers inline and Claude reads back later. Not for a one-off static report with no response capture; use a plain Artifa

• build-loop:defenseclaw-bridge

  Use when the user is working on the defenseclaw project and build-loop's Phase 1 detects defenseclaw-specific files (CLAUDE.md indicates the bridge target). Bridges build-loop's orchestrator to defenseclaw's eval/test conventions; otherwise no-op. NOT a general eval/test bridge (defenseclaw project

• drain-proposals

  Walk the cross-repo proposal backlog interactively, deciding apply/reject/defer on each item; never auto-applies. Use when the user says "drain proposals" or "review the proposal backlog".

• focused-loop-builder

  Use when the user asks to "create a custom build loop", "build a loop spec", "make a focused loop", "generate a workflow loop", "adapt a framework into a loop", or asks whether a workflow should use skill chaining. Generates declarative focused-loop specs, presets, validators, and skill-chain plans.

• guarded-batch-reconcile

  Use when reconciling parallel branches, worktrees or completed task outputs, draining a merge queue, or closing a multi-agent work wave. Establish readiness and integrate authorized work through the project's supported merge path; preserve assessment-only requests as read-only.

• handoff

  Compose a complete, durable build-loop handoff document from the current run state, and optionally launch a fresh session with it injected. Use when crossing a context boundary (context limit, planned restart, worktree GC). Triggers: 'hand off', 'handoff', 'new session', 'context limit', 'restart',

• build-loop:ibr-bridge

  Route rendered UI design updates, comparisons, and audits to the IBR plugin when installed, falling back to build-loop's own driver otherwise. Use when a build changes, compares, or audits a rendered UI and that change needs visual evidence before it can close. Not for registering a new API (use `ap

• knowledge

  Canonical build-loop-memory framework. Use when the user asks to "record a decision", "log an ADR", "write an MADR", "capture this choice", "regenerate the decisions index", "validate knowledge", "migrate feedback to decisions", or "recall <topic>". ALSO the read-only review surface (review mode): "

• logging-tracer

  Use when the user asks to "add logging", "add tracing", "improve observability", "OpenTelemetry", "structured logging", or reports silent failures or no runtime visibility. Generates stack-appropriate logging with optional OTel.

• mcp-builder

  Build, package, or debug an MCP server and its tools. Use when the user is adding MCP tools, or working on `.mcp.json`, transport, or bundling. Not for scaffolding the plugin around it (use `plugin-builder`; pair the two when a plugin exposes MCP tools).

• model-bakeoff

  Run the same bounded change across multiple models in parallel, then deterministically score and merge the best result. Use when the user says "bake-off", "compare models on this task", "which model is best at", or "A/B test these models". Not for picking a single model tier for one agent (use `mode

• model-tiering

  Recommend which model tier (e.g. Opus/Sonnet/Haiku) to use for a subagent or task. Use when the user asks "which model should I use", "is Sonnet enough or do I need Opus", or sets a segment+tier in agent frontmatter. Not for running multiple models head-to-head and scoring them (use `model-bakeoff`)

• build-loop:native-ax-driver

  Use when the build needs to automate a macOS .app without touching the hardware cursor, or the user asks to "click through the app" or "test the UI headlessly". Drives running apps via Accessibility API; self-contained Swift binary — no IBR, Playwright, or Appium required.

• optimize

  Use when the user says "optimize this", "optimization", "make X faster", "reduce <metric>", or "speed up my app". Runs a Design of Experiments test matrix — up to 6 variables in one pass — to find which variable actually moves the number. Falls back to one-at-a-time loop for single variables.

• plan-verify

  Use when build-loop Phase 2 wraps plan drafting, the user runs `/build-loop:verify-plan`, asks to "verify the plan" or "lint the plan", or any plan markdown change touches evidence, synthesis-density, risk_reason, or modifies_api fields. Runs deterministic plan-verify rules and emits findings JSON.

• plugin-builder

  Create, scaffold, or migrate a Claude Code plugin — manifest, directory layout, hooks, agents, distribution. Use when the user asks to create/build/scaffold/convert a plugin, or needs plugin.json/layout guidance. Not for building the MCP server itself once the shell exists (use `mcp-builder`; pair t

• plugin-tests

  Static-analysis test harness for Claude Code plugins. Triggers on "test plugin", "validate plugin", "check skill resolution", "run plugin tests", "lint plugin", "verify manifest", "namesake collision", "MCP registration check". Runs Python stdlib pytest scripts that catch namesake collisions, manife

• build-loop:prd-bridge

  Use when Phase 1 Assess runs, the user mentions a PRD, or asks to "ground the build in product strategy". Surfaces always-true principles and Navigation Map from the project PRD so subsequent phases reason from strategic frame; recommends prd-builder if none exists. NOT for authoring a PRD from scra

• recursive-retrospective

  Deliberate retrospective on one project's full trajectory — decide preserve/refine/redirect/reset and encode lessons into memory, agents, skills, evals, and gates. Use when the user asks to review a project's history after a substantial build, or convert a session into durable improvement. Not for t

• repo-closeout

  Compatibility alias for Repository Maintenance. Use when an existing prompt or workflow invokes repo-closeout; route all repository structure, artifact, branch, worktree, sibling consolidation, and local-main maintenance work to repo-maintenance. Deprecated: prefer repo-maintenance for new work.

• repo-maintenance

  Audit and evolve repository structure — topology, module boundaries, artifact retention, branch/worktree hygiene, and open-source readiness. Use when the user asks to reconcile branches and worktrees, merge additive work, prune stale work, clean generated artifacts, remove duplicate source, or ready

• repository-intelligence
• research
• root-cause-analysis
• runtime-parity-verification
• security-methodology
• security-scan
• self-improve
• silent-assumptions
• spec-writing
• sync-skills
• telemetry
• ui-design

Slash commands (2)

• /build-loop:feedback

  Report a bug or send feedback about the build-loop plugin

• /build-loop:run

  The one build-loop command. Describe anything in plain language — build, fix, debug, optimize, research, test, root-cause, retrospective, plan, PRD — and it routes automatically. You never pick a mode.

Subagents (29)

• advisor

  The Frontier (Fable) standing role that AUTHORS and RE-PLANS the Phase 2 plan synthesis. Generating a plan is harder than evaluating one, so the deepest reasoning pays here. The Advisor frames the goal, decomposes the work, builds the dependency graph, MECE-partitions file ownership, and — on a diag

• alignment-checker

  Advisory alignment judge for autonomous-iterate-loop queue items (plan §14.4 A). For each candidate item drained from `.build-loop/ux-queue/` + `.build-loop/issues/` + `.build-loop/proposals/`, reads the build's stated intent (`intent.md`, `goal.md`, canonical build-loop-memory constitution context,

• api-assessor

  Use this agent when the debugging symptom involves API endpoints, REST/GraphQL errors, request/response issues, authentication, rate limiting, or server-side route handlers. Examples - "500 error", "endpoint not found", "auth failed", "CORS error".

• build-loop:architecture-scout

  Read-only architecture analyst. Dispatched by build-loop orchestrator with a task type ('baseline', 'chunk-impact', 'review-rules', 'iterate-subgraph', 'learn-sync'). Decides native engine vs NavGator escalation per task. Returns ≤500-word structured JSON envelope. Owns architecture-related side eff

• assessment-orchestrator

  Use this agent when debugging requires multi-domain analysis, when the symptom is unclear about which domain is affected, or when you need to coordinate parallel assessments across database, frontend, API, and performance domains.

• build-orchestrator

  Coordinates the six-phase development loop for significant multi-step code changes (Assess → Plan → Execute → Review → Iterate → mandatory Learn). Review runs seven ordered sub-steps: Critic → Validate → Optimize (opt-in) → Fact-Check → Simplify → Auto-Resolve → Report; Iterate loops back to Review

• database-assessor

  Use this agent when the debugging symptom involves database issues, queries, migrations, schema problems, Prisma errors, PostgreSQL, connection pooling, vector/retrieval indexes, or data integrity. Examples - "slow query", "migration failed", "constraint error", "Prisma error", "connection timeout",

• design-contract-specialist

  Build-loop-owned designer and sole writer to `.build-loop/app-contract/{ui.md, data.md, traceability.json}`. In Phase 2 it loads `Skill("build-loop:ui-design")` and chooses UI design direction from the needs of the thing being built: user goal, workflow density, data shape, platform, project tokens,

• fact-checker

  Validates all rendered data, claims, and metrics before completion. Traces data sources to prevent false or unverifiable information reaching users. <example> Context: Build loop Review sub-step D — verifying claims before report user: "Run fact check on the implementation" assistant: "I'll use the

• fix-critique

  Use this agent to pressure-test a proposed fix before declaring a bug resolved. Challenges whether the fix addresses the root cause or just a symptom, checks for potential regressions, and verifies evidence exists for the claimed fix. Run after a fix is implemented but before declaring it done.

• frontend-assessor

  Use this agent when the debugging symptom involves React, hooks, rendering, UI components, state management, hydration errors, or client-side performance. Examples - "useEffect infinite loop", "component not rendering", "hydration mismatch", "state not updating".

• implementer

  Apply a single ux-fix-plan.md (or per-criterion targeted fix plan) from the build-loop Phase 5 work list. One queue entry per invocation. Returns changed files + status. Designed for parallel fan-out (≤4 in flight per orchestrator pass).

• independent-auditor

  LLM-grade escalation path for the boundary-gated commit auditor. The primary mechanism is the deterministic PreToolUse hook script (`scripts/audit_before_commit.py`); this agent fires only when the orchestrator wants a deeper read on a specific commit (e.g., before squash-merge of a multi-chunk buil

• leak-scanner

  Static scan for memory and resource leaks in long-lived code paths: unbounded collections fed by external input, terminal-only eviction predicates, registration without deregistration, retain cycles, spawn-without-reap, and accumulating stream buffers. <example> Context: Build loop Review sub-step D

• mock-scanner

  Fast, lightweight scan for residual mock, placeholder, fake, private, or secret data in production/public code paths. <example> Context: Build loop Review sub-step D — scanning for mock data before release user: "Scan for any leftover test data in production code" assistant: "I'll use the mock-scann

• optimize-runner

  Executes the optimization loop. Generates hypotheses, makes atomic changes within scope, measures metrics, keeps improvements or reverts regressions. Runs autonomously until convergence or budget exhaustion.

• overfitting-reviewer

  Reviews optimization results for overfitting, Goodhart violations, and test-gaming shortcuts. Read-only adversarial review.

• performance-assessor

  Use this agent when the debugging symptom involves slowness, latency, timeouts, memory leaks, CPU usage, bottlenecks, or optimization needs. Examples - "app is slow", "memory keeps increasing", "timeout errors", "high CPU usage".

• plan-critic

  Adversarial read-only critique of a Phase 2 plan markdown file for non-deterministic issues that grep cannot catch — alternatives considered, MECE scope quality, marker adequacy, and headline drift across sections. Pair with `scripts/plan_verify.py` (deterministic verifier) — run plan-verify first,

• promotion-reviewer

  Advisory judge for Phase 6 Learn experimental-artifact promotion. Reads a candidate experimental skill or agent (drafted by `self-improvement-architect`), its A/B track record, and the build-loop constitution, then returns a variance-shaped verdict (`approve | rethink | new_approach`). Never blocks

• recurring-pattern-detector

  Scans `.build-loop/state.json.runs[]` for patterns that recur across 3+ runs (same phase failing, same diagnostic command, same file churn, same manual user intervention). Emits a structured JSON proposal list. Pattern-matching only — no authoring, no judgment. <example> Context: Build-loop Phase 6

• retrospective-synthesizer

  Post-push retrospective synthesizer. Reads the session transcript JSONL + state.json + intent + plan after the Phase 4 Report closing push, and writes a structured 11-section retrospective to `.build-loop/retrospectives/<YYYY-MM-DD>/<run-id>.md` plus a ≤5-line `<run-id>.summary.md` surfaced inline.

• root-cause-investigator

  Use this agent when a debugging symptom needs deep causal analysis beyond surface-level diagnosis. Builds a causal tree (not a single chain) to explore multiple potential root causes in parallel. Flags when investigation reaches external/environmental boundaries or when internet research is needed.

• scope-auditor

  Read-only Plan→Execute boundary check. For every commit that changes a public function/component/type signature, traces every caller-site outside the commit's owned-files, then either confirms `internal_only: true` or appends the missing caller files to the appropriate commit's owned-files list. Pre

• security-reviewer

  Adversarial read-only security review of implementer output against OWASP LLM Top 10, OWASP Agentic Top 10, OWASP Web Top 10 (HTTP boundary only), and starter MITRE ATLAS techniques. Runs in Phase 4 Review sub-step A in parallel with `independent-auditor` at `scope: "build"`, but only when Assess fl

• self-improvement-architect

  Takes a pattern proposal from `recurring-pattern-detector` and drafts a concrete experimental SKILL.md (or agent definition) the build-loop can use immediately. Uses the `plugin-dev:skill-development` or `plugin-dev:agent-development` skill as the authoring reference. Writes output to `.build-loop/s

• synthesis-critic

  Read-only model-based critic for the subjective synthesis dimensions (`copy_tone`, `empty_state`) that `attestation_lint.py` cannot grade deterministically. Runs in Phase 4.5 after the attestation lint, only on commits that touch UI files. WARN-only — never blocks a commit. <example> Context: Implem

• transcript-pattern-miner

  Scans local Claude Code session transcripts for recurring patterns worth promoting to skills, agents, hooks, or feedback notes. Pure stdlib regex miner — no LLM calls, no network. Five categories: user corrections, repeated tool sequences, cross-project file patterns, manual command rituals, and obs

• ui-validator

  Run deterministic UI scans against the running dev server: layout collisions, touch-target violations, console errors, hydration stability, computed-style diffs vs prior baseline, and per-route visual SSIM. Used at Phase 3 chunk-close on UI-touching chunks and at Phase 4 Review sub-step B on every b

Hooks (18)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/session-start-tool-state.sh" 2>/dev/null; exit 0

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/session-start-architecture.sh" </dev/null >/dev/null 2>&1; exit 0

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/session-start-rally-point.sh" 2>/dev/null; exit 0

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/closeout.sh" session-start </dev/null 2>/dev/null; exit 0

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/session-start-codex-hook-trust.sh" </dev/null 2>/dev/null || printf '{}'

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/pre-edit-architecture.sh" >/dev/null 2>&1; exit 0

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/pre-edit-rally-point.sh"; exit 0

• PreToolUse

  root="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; hook="$root/scripts/hooks/pre_bash_dispatch.sh"; if [ -x "$hook" ]; then "$hook"; else printf '{}'; fi

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/pre-edit-rally-point.sh"; exit 0

• PreToolUse

  if [ -f "${CLAUDE_PROJECT_DIR:-$PWD}/.build-loop/state.json" ]; then r="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; s=75; if [ "${BUILD_LOOP_NATIVE_HOOKS:-}" != off ] && [ -x "$r/bin/native/bl" ] &&

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/post-push-closeout.sh" >/dev/null 2>&1; exit 0

• PostToolUse

  if [ -f "${CLAUDE_PROJECT_DIR:-$PWD}/.build-loop/state.json" ]; then r="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; s=75; if [ "${BUILD_LOOP_NATIVE_HOOKS:-}" != off ] && [ -x "$r/bin/native/bl" ] &&

• Stop

  root="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; hook="$root/scripts/hooks/stop_finalize.sh"; if [ -x "$hook" ]; then "$hook"; else printf '{}'; fi

• Stop

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/closeout.sh" stop 2>/dev/null; exit 0

• Stop

  if [ -f "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/scripts/commit_state_check.py" ]; then python3 "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/scripts/commit_state_check.py" --workdir "${CLAUDE_PROJEC

• Stop

  bash "${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}/hooks/stop-transcript-sweep.sh" all 2>/dev/null || printf '{}'

• SessionEnd

  root="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; s="$root/scripts/hooks/session_end_retro_sweep.py"; tp=$(python3 -c 'import sys,json;print(json.load(sys.stdin).get("transcript_path",""))' 2>/dev/nu

• PostToolUseFailure

  if [ -f "${CLAUDE_PROJECT_DIR:-$PWD}/.build-loop/state.json" ]; then r="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; s=75; if [ "${BUILD_LOOP_NATIVE_HOOKS:-}" != off ] && [ -x "$r/bin/native/bl" ] &&

Similar plugins