Skip to content

notque/vexjoy-agent / skills/process/workflow

workflow

Verified

Structured work: multi-phase tasks, feature builds, planning, objective loops, hill climbing.

FileKindSize
SKILL.mdskill md13.2 KB
references/adr-template.mdmarkdown9.4 KB
references/agent-upgrade.mdmarkdown12.5 KB
references/article-evaluation-pipeline.mdmarkdown8.9 KB
references/article-evaluation-pipeline/references/report-template.mdmarkdown2.5 KB
references/article-evaluation-pipeline/references/wabi-sabi-classification.mdmarkdown2.4 KB
references/auto-pipeline.mdmarkdown12.5 KB
references/auto-pipeline/references/pipeline-catalog.jsonconfig15.0 KB
references/auto-pipeline/references/pipeline-catalog.mdmarkdown4.3 KB
references/build_dag.pyscript12.5 KB
references/chain-composer.mdmarkdown20.4 KB
references/chain-composer/references/canonical-chains.mdmarkdown13.9 KB
references/comprehensive-review-workflow.jsscript19.3 KB
references/comprehensive-review.mdmarkdown27.8 KB
references/comprehensive-review/references/output-templates.mdmarkdown10.6 KB
references/comprehensive-review/references/wave-0-per-package.mdmarkdown5.6 KB
references/comprehensive-review/references/wave-1-foundation.mdmarkdown10.4 KB
references/comprehensive-review/references/wave-2-deep-dive.mdmarkdown7.3 KB
references/comprehensive-review/references/wave-3-adversarial.mdmarkdown7.4 KB
references/dag-compatibility-matrix.mdmarkdown13.0 KB
references/dag-composition-patterns.mdmarkdown5.0 KB
references/dag-orchestration-advanced.mdmarkdown6.3 KB
references/dag-orchestration-examples.mdmarkdown11.4 KB
references/dag-skill-patterns.mdmarkdown12.5 KB
references/de-ai-pipeline.jsscript14.6 KB
references/de-ai-pipeline.mdmarkdown6.3 KB
references/discover_skills.pyscript12.1 KB
references/do-perspectives.mdmarkdown11.5 KB
references/doc-pipeline.mdmarkdown9.2 KB
references/domain-research.mdmarkdown32.8 KB
references/domain-research/references/task-type-guide.mdmarkdown11.4 KB
references/explore-pipeline.jsscript18.6 KB
references/explore-pipeline.mdmarkdown15.0 KB
references/fan-out-workflow.jsscript9.7 KB
references/fan-out-workflow.pyscript10.4 KB
references/feedback-loop-construction.mdmarkdown14.3 KB
references/fl-design.mdmarkdown9.6 KB
references/fl-error-handling.mdmarkdown8.5 KB
references/fl-implement.mdmarkdown7.6 KB
references/fl-pipeline.mdmarkdown6.0 KB
references/fl-plan.mdmarkdown11.0 KB
references/fl-release.mdmarkdown3.8 KB
references/fl-shared.mdmarkdown3.6 KB
references/fl-validate.mdmarkdown4.5 KB
references/github-profile-rules.mdmarkdown10.5 KB
references/github-profile-rules/references/rule-categories.mdmarkdown6.5 KB
references/hc-SPEC.mdmarkdown3.3 KB
references/hc-domain-playbooks.mdmarkdown15.4 KB
references/hc-ledger.mdmarkdown3.3 KB
references/hc-profiling-tools.mdmarkdown3.7 KB
references/hill-climb.mdmarkdown9.3 KB
references/hook-development-pipeline.mdmarkdown12.9 KB
references/mcp-pipeline-builder.mdmarkdown16.3 KB
references/mcp-pipeline-builder/references/analysis-checklist.mdmarkdown6.2 KB
references/mcp-pipeline-builder/references/design-rules.mdmarkdown7.1 KB
references/mcp-pipeline-builder/references/evaluation-guide.mdmarkdown7.6 KB
references/mcp-pipeline-builder/references/python-scaffold-template.mdmarkdown9.5 KB
references/mcp-pipeline-builder/references/ts-scaffold-template.mdmarkdown1.6 KB
references/mcp-pipeline-builder/scripts/assemble-scaffold.pyscript6.3 KB
references/mcp-pipeline-builder/scripts/register_mcp.pyscript6.9 KB
references/mcp-pipeline-builder/templates/client-cli.ts.tmplother682 B
references/mcp-pipeline-builder/templates/client-http.ts.tmplother1.4 KB
references/mcp-pipeline-builder/templates/index.ts.tmplother1.1 KB
references/mcp-pipeline-builder/templates/package.json.tmplother477 B
references/mcp-pipeline-builder/templates/readme.md.tmplother1.1 KB
references/mcp-pipeline-builder/templates/tools.ts.tmplother3.0 KB
references/mcp-pipeline-builder/templates/ts-scaffold.tmplother556 B
references/mcp-pipeline-builder/templates/tsconfig.json.tmplother408 B
references/ol-SPEC.mdmarkdown2.4 KB
references/ol-state-file.mdmarkdown2.9 KB
references/pipeline-index.jsonconfig23.9 KB
references/pipeline-orchestrator.mdmarkdown15.3 KB
references/pipeline-orchestrator/orchestration-patterns.mdmarkdown8.1 KB
references/pipeline-orchestrator/preferred-patterns.mdmarkdown4.6 KB
references/pipeline-retro.mdmarkdown19.0 KB
references/pipeline-scaffolder.mdmarkdown22.4 KB
references/pipeline-scaffolder/references/architecture-rules.mdmarkdown18.9 KB
references/pipeline-scaffolder/references/generated-skill-template.mdmarkdown1.9 KB
references/pipeline-scaffolder/references/pipeline-spec-format.mdmarkdown36.8 KB
references/pipeline-scaffolder/references/step-menu.mdmarkdown21.5 KB
references/pipeline-scaffolder/scripts/assemble-skill.pyscript6.3 KB
references/pipeline-scaffolder/templates/phases/decision-planning.md.tmplother1.2 KB
references/pipeline-scaffolder/templates/phases/domain-extension.md.tmplother1.5 KB
references/pipeline-scaffolder/templates/phases/generation.md.tmplother427 B
references/pipeline-scaffolder/templates/phases/git-release.md.tmplother1.1 KB
references/pipeline-scaffolder/templates/phases/interaction.md.tmplother965 B
references/pipeline-scaffolder/templates/phases/learning-retro.md.tmplother1.5 KB
references/pipeline-scaffolder/templates/phases/observation.md.tmplother1.3 KB
references/pipeline-scaffolder/templates/phases/research-gathering.md.tmplother1.2 KB
references/pipeline-scaffolder/templates/phases/review.md.tmplother930 B
references/pipeline-scaffolder/templates/phases/safety-guarding.md.tmplother1.7 KB
references/pipeline-scaffolder/templates/phases/structuring.md.tmplother361 B
references/pipeline-scaffolder/templates/phases/synthesis-reporting.md.tmplother1.9 KB
references/pipeline-scaffolder/templates/phases/validation.md.tmplother1.1 KB
references/pipeline-scaffolder/templates/skill-template.md.tmplother12.0 KB
references/pipeline-test-runner.mdmarkdown16.7 KB
references/pl-ambiguity-triage.mdmarkdown2.7 KB
references/pl-check-dimensions.mdmarkdown7.4 KB
references/pl-check-errors.mdmarkdown824 B
references/pl-check-verdict-format.mdmarkdown3.2 KB
references/pl-check.mdmarkdown6.5 KB
references/pl-context-boundary.mdmarkdown1.6 KB
references/pl-depth-first-interview.mdmarkdown11.6 KB
references/pl-empirical-prototype.mdmarkdown825 B
references/pl-executor-ready-plan-template.mdmarkdown7.7 KB
references/pl-human-source-elicitation.mdmarkdown1.5 KB
references/pl-manage.mdmarkdown5.1 KB
references/pl-pause-confirm-and-errors.mdmarkdown2.1 KB
references/pl-pause-extract-decisions.mdmarkdown3.0 KB
references/pl-pause-gather-steps.mdmarkdown2.3 KB
references/pl-pause-synthesize-fields.mdmarkdown2.3 KB
references/pl-pause-write-templates.mdmarkdown5.3 KB
references/pl-pause.mdmarkdown6.5 KB
references/pl-plan-files.mdmarkdown8.4 KB
references/pl-pre-plan.mdmarkdown11.6 KB
references/pl-resume.mdmarkdown12.3 KB
references/pl-spec.mdmarkdown5.2 KB
references/pr-fix-loop.mdmarkdown10.3 KB
references/pr-fix-loop/references/message-formats.mdmarkdown1.6 KB
references/pr-fix-loop/references/publish.mdmarkdown5.4 KB
references/pr-fix-loop/references/review-checklist.mdmarkdown3.4 KB
references/pr-pipeline/references/pr-templates.mdmarkdown5.4 KB
references/pr-pipeline/references/preflight-checklist.mdmarkdown2.8 KB
references/pr-pipeline/references/retro-adr-phases.mdmarkdown2.7 KB
references/pr-pipeline/references/review-fix-loop.mdmarkdown2.0 KB
references/project-coordinator.mdmarkdown6.5 KB
references/project-coordinator/agent-capability-map.mdmarkdown5.4 KB
references/project-coordinator/communication-protocols.mdmarkdown4.5 KB
references/project-coordinator/coordination-playbook.mdmarkdown3.7 KB
references/project-coordinator/death-loop-prevention.mdmarkdown3.6 KB
references/project-coordinator/error-catalog.mdmarkdown2.7 KB
references/project-coordinator/parallel-execution-patterns.mdmarkdown2.8 KB
references/project-coordinator/preferred-patterns.mdmarkdown5.9 KB
references/project-coordinator/todowrite-integration.mdmarkdown5.6 KB
references/research-pipeline.jsscript15.2 KB
references/skill-creation-pipeline.mdmarkdown17.1 KB
references/system-upgrade.mdmarkdown12.8 KB
references/systematic-debugging.mdmarkdown11.0 KB
references/systematic-refactoring.mdmarkdown11.4 KB
references/toolkit-improvement.jsscript39.0 KB
references/toolkit-improvement.mdmarkdown20.5 KB
references/toolkit-improvement/references/adr-template.mdmarkdown10.5 KB
references/toolkit-improvement/references/agent-roster.mdmarkdown15.8 KB
references/workflow-helpers.jsscript12.1 KB
references/workflow-orchestrator.mdmarkdown20.8 KB
references/workflow-orchestrator/references/plan-template.mdmarkdown1.3 KB
references/workflow-orchestrator/references/task-patterns.mdmarkdown23.3 KB
references/workflow-orchestrator/scripts/assemble-plan.pyscript6.9 KB
references/workflow-orchestrator/scripts/validate.pyscript14.4 KB
references/workflow-orchestrator/templates/plan-template.json.tmplother904 B

references/fan-out-workflow.js

View on GitHub
// fan-out-workflow.js
//
// Generic, parameterized native fan-out/synthesize Workflow. This is the
// default deterministic-runtime executor for Complex / tier-4 work that has NO
// named pipeline (a `pick=null` complexity-trigger from /do Phase 4 Step 1b).
// Unlike comprehensive-review-workflow.js (a STATIC Wave-1 roster + dynamic
// tail), this workflow's roster is supplied ENTIRELY by the caller — there are
// no fixed agent/skill literals in source. The prose `dispatching-parallel-
// agents` flow is the always-safe floor when the Workflow tool is absent.
//
// Runtime contract (see docs/dynamic-workflows-vs-vexjoy-diff.md):
//   - meta is a pure object literal (name + description + contract) parsed
//     before the body.
//   - parallel(thunks) is a hard barrier; a failed agent resolves to null.
//   - agent({prompt, schema, model, agentType}) forces a StructuredOutput tool
//     call, validates against schema at the tool layer, and returns a typed
//     object — no markdown re-parse, no disk read.
//   - budget.remaining() returns run-wide tokens left; agent() throws when
//     exhausted. The synthesize pass is budget-aware (no unbounded loop).
//   - Wall-clock and randomness are unavailable by design (determinism is
//     bit-stable across replay). This script uses neither.

import {
  mandatoryInjections,
  modelFor,
  skillDirectives,
  validateAgentName,
  validateModelOverride,
  validateRoster,
} from "./workflow-helpers.js";

export const meta = {
  name: "fan-out-workflow",
  description:
    "Generic native fan-out/synthesize Workflow for Complex / tier-4 work with no named pipeline: dispatch a caller-supplied roster of specialists in a single parallel barrier (each attaching its FULL skill stack by name via one exact Skill-tool call per skill, plus the /do mandatory injections), then synthesize the typed worker results in-memory with one budget-aware synthesizer. The roster, skills, lenses, and synthesizer are all caller-supplied — the floor is the prose dispatching-parallel-agents flow.",
  // --- Conformance contract (pure literal — no calls/variables; see
  //     scripts/validate-workflow-conformance.py + adr/native-fast-path-portable-floor.md
  //     Stage 2). This is a FULLY-DYNAMIC-roster contract: the roster is
  //     caller-supplied, so there are NO static agent/skill literals to pin.
  //     The gate asserts the STRUCTURAL invariant (source emits an exact Skill-tool
  //     call derived from a roster variable AND dispatches agentType from a
  //     roster variable), NOT specific names. name + description stay BEFORE this
  //     nested object so the non-greedy meta-name parser in workflow-registry.py
  //     still resolves meta.name.
  contract: {
    // Phase titles this script enters at runtime via enterPhase(). Order matters.
    phases: ["fan-out", "synthesize"],
    // Fully-dynamic roster: caller-supplied at run({roster}). No static names to
    // pin — the gate asserts the structural invariant instead.
    roster: { dynamic: true },
    // No static barrier to count: every dispatched agent comes from the runtime
    // roster (roster.length workers + 1 synthesizer).
    agents: { dynamic: true },
    // Data-driven fan-out: count + names are caller-supplied (honest limit — the
    // gate asserts SHAPE + the structural Skill-tool-call/agentType invariant, NOT COUNT).
    dynamic: true,
  },
};

// --- Schemas (mirror the STYLE of comprehensive-review-workflow.js / -----------
//     skills/shared-patterns/schemas/). Worker results and the synthesis are
//     schema-validated typed objects, not re-parsed markdown.

// One worker's typed output. `findings` mirrors the FINDING/WAVE_OUTPUT shape so
// downstream synthesis is uniform regardless of the worker's lens.
const FINDING_SCHEMA = {
  type: "object",
  required: ["title"],
  properties: {
    title: { type: "string" },
    location: { type: "string" },
    severity: { type: "string", enum: ["critical", "high", "medium", "low", "info"] },
    detail: { type: "string" },
  },
};

const WORKER_SCHEMA = {
  type: "object",
  required: ["verdict", "summary"],
  properties: {
    verdict: { type: "string", enum: ["PASS", "CONCERN", "BLOCK", "INFO"] },
    summary: { type: "string", minLength: 1 },
    findings: { type: "array", items: FINDING_SCHEMA },
    lens: { type: "string" },
  },
};

// The single synthesizer's typed output over the worker results.
const SYNTH_SCHEMA = {
  type: "object",
  required: ["verdict", "summary"],
  properties: {
    verdict: { type: "string", enum: ["PASS", "CONCERN", "BLOCK", "INFO"] },
    summary: { type: "string", minLength: 1 },
    key_findings: { type: "array", items: FINDING_SCHEMA },
    recommendations: { type: "array", items: { type: "string" } },
  },
};

// --- Helpers ------------------------------------------------------------------

// Defensive phase marker: the native runtime guarantees agent/parallel/budget,
// but does NOT document a phase() global. Guard the call so the real runtime
// never throws if phase is absent, while the conformance harness's mock records
// the entered phase. Phase titles match meta.contract.phases.
function enterPhase(title) {
  if (typeof phase === "function") {
    phase(title);
  }
}

// Build one worker's prompt from its roster entry. The roster entry supplies the
// dispatched specialist (agentType), the FULL skill stack it attaches by name
// (one exact Skill-tool call per element of r.skills — resolves path-independent inside a
// native Workflow agent() dispatch, proven this session), and the lens that
// focuses its pass. `scope` is the shared diff/task descriptor. The Skill
// directives are built FROM the roster variable r.skills — this is the fully-
// dynamic structural invariant the conformance gate asserts. Every prompt also
// embeds the /do mandatory injections (completeness/density/base-instructions/
// reference-loading) so a workflow agent gets the same context as a direct /do
// dispatch.
function workerPrompt(r, scope) {
  const lens = r.lens ? `Apply this lens: ${r.lens}.` : "Apply your specialist lens.";
  return (
    `You are ${r.agentType}. ${lens}` +
    skillDirectives(r.skills) +
    `\nWork this scope:\n${JSON.stringify(scope)}\n` +
    `Return a typed result: verdict (PASS|CONCERN|BLOCK|INFO), a summary, and any ` +
    `findings within your lens. Stay within your lens — the synthesizer merges across workers.` +
    mandatoryInjections()
  );
}

// --- Workflow body ------------------------------------------------------------
//
// run({scope, tier, roster, synthAgentType, fixThreshold, modelOverride}):
//   - scope: the shared task/diff descriptor passed to every worker.
//   - tier: right-size-review tier (carried into scope for the workers; this
//     workflow does not gate phases on tier — the CALLER sizes the roster).
//   - roster: [{agentType, skills, lens}] — caller-supplied; the fan-out set.
//     `skills` is a LIST (the full /do Phase-3 stack), one exact Skill-tool call per element.
//   - synthAgentType: the synthesizer agent (default a general synthesizer).
//   - fixThreshold: min budget to attempt the synthesis pass (default 8000).
//   - modelOverride: a model the owner named for this task. When set, every
//     agent runs on it. Unset: workers run the `work` model and the
//     synthesizer inherits the session model (`lead`). See modelFor().

export default async function run({
  scope,
  tier,
  roster,
  synthAgentType,
  fixThreshold,
  modelOverride,
} = {}) {
  // Reject a bad model name before any dispatch.
  validateModelOverride(modelOverride);
  // Validate the complete caller-supplied dispatch plan before entering a phase
  // or invoking agent(), so one bad name rejects the whole fan-out.
  const workers = validateRoster(roster, "roster");
  // Default general synthesizer: a general-purpose worker (repo agents are
  // retired, plan 009). The caller overrides via synthAgentType.
  const synthesizer = validateAgentName(
    synthAgentType || "general-purpose",
    "synthAgentType",
  );
  const minSynthBudget = typeof fixThreshold === "number" ? fixThreshold : 8000;

  // Phase fan-out: one hard barrier over the caller-supplied roster. Each slot
  // dispatches the roster's specialist via agentType (a runtime variable) and
  // embeds one exact Skill-tool call per element of r.skills (the full stack) plus
  // the /do mandatory injections. A failed slot resolves to null; nulls are
  // filtered before synthesis.
  enterPhase("fan-out");
  const rawResults = await parallel(
    workers.map((r) => () =>
      agent({
        prompt: workerPrompt(r, scope),
        schema: WORKER_SCHEMA,
        model: modelFor("work", modelOverride),
        agentType: r.agentType,
        phase: "fan-out",
      }),
    ),
  );
  const results = rawResults.filter((x) => x != null);

  // Phase synthesize: one synthesizer over the typed worker results in-memory
  // (no disk). Budget-aware — skip the pass if the run can no longer afford it,
  // and report the workers directly rather than looping unboundedly.
  enterPhase("synthesize");
  let synthesis = null;
  if (results.length > 0 && budget.remaining() >= minSynthBudget) {
    synthesis = await agent({
      prompt:
        `Synthesize these ${results.length} typed specialist results into one ` +
        `verdict + summary. Merge overlapping findings, keep the highest severity, ` +
        `and list concrete recommendations. Results (typed, in-memory):\n` +
        `${JSON.stringify(results)}`,
      schema: SYNTH_SCHEMA,
      model: modelFor("lead", modelOverride),
      agentType: synthesizer,
      phase: "synthesize",
    });
  }

  return {
    tier: typeof tier === "number" ? tier : null,
    workers_ran: results.length,
    roster: workers.map((r) => ({ agentType: r.agentType, skills: r.skills, lens: r.lens })),
    synthesis,
    budget_remaining: budget.remaining(),
  };
}
planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall