Crawler Summary

ohspec answer-first brief

Use when 需要 RFC 技术规范、需求分析或 API 契约设计。Triggers on "RFC", "OHSpec", "/ohspec". --- name: ohspec description: Use when 需要 RFC 技术规范、需求分析或 API 契约设计。Triggers on "RFC", "OHSpec", "/ohspec". allowed-tools: Task, AskUserQuestion, request_user_input, Read, Write, Glob, Grep, Bash, spawn_agent, wait, send_input, close_agent --- OHSpec - 需求分析与设计规范 AI辅助需求分析与设计规范生成,强调多代理编排、结构化产物和质量门禁。 Architecture 架构概览与职责划分。 **核心职责**: 1. 协调工作流:启动子代理,管理阶段转换,确保质量门禁 2. 委托执行:优先委托(Claude Code/Task 子代理环境);Task 不可用时启用 Codex 兼容回退 Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Freshness

Last checked 4/15/2026

Best For

ohspec is best for scope workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

Claim this agent
Agent DossierGitHubSafety: 94/100

ohspec

Use when 需要 RFC 技术规范、需求分析或 API 契约设计。Triggers on "RFC", "OHSpec", "/ohspec". --- name: ohspec description: Use when 需要 RFC 技术规范、需求分析或 API 契约设计。Triggers on "RFC", "OHSpec", "/ohspec". allowed-tools: Task, AskUserQuestion, request_user_input, Read, Write, Glob, Grep, Bash, spawn_agent, wait, send_input, close_agent --- OHSpec - 需求分析与设计规范 AI辅助需求分析与设计规范生成,强调多代理编排、结构化产物和质量门禁。 Architecture 架构概览与职责划分。 **核心职责**: 1. 协调工作流:启动子代理,管理阶段转换,确保质量门禁 2. 委托执行:优先委托(Claude Code/Task 子代理环境);Task 不可用时启用 Codex 兼容回退

OpenClawself-declared

Public facts

4

Change events

1

Artifacts

0

Freshness

Apr 15, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Apr 15, 2026

Vendor

Clipsheep6

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Setup snapshot

git clone https://github.com/clipsheep6/ohspec.git
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Clipsheep6

profilemedium
Observed Apr 15, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Apr 15, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

0

Examples

6

Snippets

0

Languages

typescript

Parameters

Executable Examples

text

+-------------------------------------------------------------------+
| Orchestrator (你)                                                  |
| - 协调流程 / 复杂度路由 / 质量门禁 / 维护三文件                     |
+-------------------------------+-----------------------------------+
| Subagents                     | Artifacts                         |
| dispatcher-agent /            | rfc.md / findings.json /           |
| analyze-agent /               | progress.json                      |
| design-agent /                |                                    |
| audit-agent /                 |                                    |
+-------------------------------+-----------------------------------+
| Optional export: /ohspec:export -> rfc.digest.json + tasks.json    |
+-------------------------------------------------------------------+

text

用户需求
  -> 初始化三文件(rfc.md/findings.json/progress.json)
  -> PRECHECK:快速需求预检(30秒过滤不可行需求)
  -> ASSESS:确定工具与 scan scope,写入 progress.json + audit_log
  -> 快速意图澄清(≤2问题,确保扫描准确性)
  -> dispatcher-agent 基线扫描(scan-of-record)
  -> 深度技术澄清(基于扫描结果)
  -> 复杂度路由 + 路由信号
  -> analyze -> design -> precheck -> audit
  -> RFC 输出
  -> 可选 /ohspec:export 生成机读件

bash

/ohspec "为音频服务增加 3D 音效开关"

bash

# 简单功能需求
/ohspec "为音频服务增加 3D 音效开关"

# 跨模块需求
/ohspec "实现用户认证模块与权限系统集成"

# 性能优化需求
/ohpec "优化数据库查询响应时间至 100ms 以内"

bash

# 设计新的 API 契约
/ohspec "设计用户注册 API 契约,包含邮箱验证和密码强度检查"

# 修改现有 API
/ohspec "重构支付接口,支持多种支付方式"

bash

# 生成 RFC 后导出 digest 和 tasks
/ohspec "支付系统重构"

# 然后执行导出(手动触发)
/ohspec:export

# 输出:
# - rfc.digest.json (面向编码 Agent 的摘要)
# - tasks.json (可执行任务清单,支持 depends_on)

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Use when 需要 RFC 技术规范、需求分析或 API 契约设计。Triggers on "RFC", "OHSpec", "/ohspec". --- name: ohspec description: Use when 需要 RFC 技术规范、需求分析或 API 契约设计。Triggers on "RFC", "OHSpec", "/ohspec". allowed-tools: Task, AskUserQuestion, request_user_input, Read, Write, Glob, Grep, Bash, spawn_agent, wait, send_input, close_agent --- OHSpec - 需求分析与设计规范 AI辅助需求分析与设计规范生成,强调多代理编排、结构化产物和质量门禁。 Architecture 架构概览与职责划分。 **核心职责**: 1. 协调工作流:启动子代理,管理阶段转换,确保质量门禁 2. 委托执行:优先委托(Claude Code/Task 子代理环境);Task 不可用时启用 Codex 兼容回退

Full README

name: ohspec description: Use when 需要 RFC 技术规范、需求分析或 API 契约设计。Triggers on "RFC", "OHSpec", "/ohspec". allowed-tools: Task, AskUserQuestion, request_user_input, Read, Write, Glob, Grep, Bash, spawn_agent, wait, send_input, close_agent

OHSpec - 需求分析与设计规范

AI辅助需求分析与设计规范生成,强调多代理编排、结构化产物和质量门禁。

Architecture

架构概览与职责划分。

+-------------------------------------------------------------------+
| Orchestrator (你)                                                  |
| - 协调流程 / 复杂度路由 / 质量门禁 / 维护三文件                     |
+-------------------------------+-----------------------------------+
| Subagents                     | Artifacts                         |
| dispatcher-agent /            | rfc.md / findings.json /           |
| analyze-agent /               | progress.json                      |
| design-agent /                |                                    |
| audit-agent /                 |                                    |
+-------------------------------+-----------------------------------+
| Optional export: /ohspec:export -> rfc.digest.json + tasks.json    |
+-------------------------------------------------------------------+

核心职责

  1. 协调工作流:启动子代理,管理阶段转换,确保质量门禁
  2. 委托执行:优先委托(Claude Code/Task 子代理环境);Task 不可用时启用 Codex 兼容回退
  3. 管理上下文:将繁重工作委托给子代理,保持主上下文清洁
  4. 确保质量:执行强制检查,验证输出,维护 RFC 标准

关键产物rfc.mdfindings.jsonprogress.json(三文件是 scan-of-record 与质量审计入口)。

Hard Constraints

  • 三文件必须先落盘rfc.mdfindings.jsonprogress.json 必须在扫描前初始化
  • 默认委托 dispatcher-agent 执行基线扫描(scan-of-record);Task 不可用时使用 Codex 兼容回退
  • Codex 并行优先:当 Task 不可用且 spawn_agent 可用时,MEDIUM/COMPLEX 在 dispatcher 阶段必须优先使用 spawn_agent 并行分区扫描;失败才降级串行,并在 progress.json.tooling + audit_log 记录原因
  • 工具选择以 ASSESS 为准(跨 CLI):搜索/语义检索/并行策略必须由 ASSESS 决策并落盘到 progress.json.tooling;后续阶段只“读取并执行”(详见 phases/assess.md
  • 所有详细扫描结果写入 findings.json
  • 子代理返回 JSON 摘要(≤500 tokens)
  • 每阶段结束更新 progress.json
  • DFX 必须量化,禁止模糊描述
  • 禁止开放式问题,必须选项式
  • 机读件不写进 RFC:通过 /ohspec:export 手动生成 rfc.digest.json(可选 tasks.json
  • 澄清/门禁提问工具优先级:优先用 AskUserQuestion(若可用);否则 Codex CLI 用 request_user_input;若工具不可用/被禁用,输出"选项式问题 + 影响 + 建议"的文本并暂停,不得进入 plan/design/audit
  • 禁止假设:找不到证据就补扫或阻断,不得编造设置键/接口/默认值

Codex 兼容回退(Task 不可用)

当无法使用 Task 子代理时(例如 Codex 环境),按以下优先级执行:

  1. 优先:Codex 子代理并行(spawn_agent)分区扫描(MEDIUM/COMPLEX 默认启用)

    • 分区建议(4 个)entrypoints(入口/路由/CLI)、config(配置/环境变量/feature flags)、deps(依赖/构建/部署/IaC)、tests_obs(测试/日志/指标/追踪/告警)
    • 子代理硬约束:只返回 JSON 摘要;不得直接写 rfc.md/findings.json/progress.json
    • 汇总规则:编排器 wait 后合并到 findings.json.confirmed.key_files/facts;冲突以“证据锚点更强/更靠近入口”优先,并写入 audit_log
    • 失败降级spawn_agent 不可用/异常/超时 → 退回“最小化 scan-of-record(串行)”,并记录 progress.json.tooling.execution_mode=serial + 原因
  2. 降级:最小化 scan-of-record(串行)

  • 优先使用 rg(其次 ag/grep)做关键词预过滤,快速定位候选关键文件
  • 必须排除生成物目录:避免把历史 RFC/缓存当作"证据"并拉爆上下文(示例:rg --glob '!**/.ohspec/**' --glob '!**/.claude/ohspec/**' --glob '!**/node_modules/**' --glob '!**/dist/**' --glob '!**/build/**' ...
  • 先落盘三文件(rfc.md/findings.json/progress.json),再开始任何扫描
  • ASSESS 必须先落盘:在进入任何内容级扫描前,先用 ASSESS 选定工具与 scan_scope,并写入 progress.json.tooling + phases.assess + audit_log
  • 产出必须写入 findings.confirmed.key_files(≥3 且覆盖入口/配置/依赖或测试/可观测)
  • 同时写入 findings.confirmed.facts(SIMPLE ≥ 1;MEDIUM/COMPLEX ≥ 3,项目事实:配置/存储/权限/错误码/线程模型/可观测等,每条附证据锚点)
  • 禁止假设:找不到证据就补扫/阻断,不得编造设置键/接口/默认值
  • 第一分钟基线:开始深度 Read/设计推演前,必须先把 key_files+facts 落盘(否则中断会导致三文件"空壳")
  • 记录到 progress.json.toolingaudit_log

Routing Signals

基于复杂度和信号动态路由,不强制执行所有阶段。

| 信号 | 触发条件 | Agent | 说明 | |------|----------|-------|------| | SKIP_ANALYZE | 需求明确、单文件 | 跳过 analyze | 快速通道 | | LOAD_DIPLOMAT | 跨子系统依赖 | diplomat-agent | 处理跨模块依赖 | | TRIGGER_SPIKE | 技术不确定 | prototyper-agent | 触发 Spike 验证 | | SIMPLIFY_CLARIFY | 详细需求 | 简化澄清 | 减少澄清轮次 |

复杂度路由

| 级别 | 特征 | 模式 | |------|------|------| | SIMPLE | 单文件,<50行 | 快速通道 | | MEDIUM | 多文件,单子系统 | 标准流程 | | COMPLEX | 跨子系统,架构级 | 完整流程 + spike |

Execution Flow

用户需求
  -> 初始化三文件(rfc.md/findings.json/progress.json)
  -> PRECHECK:快速需求预检(30秒过滤不可行需求)
  -> ASSESS:确定工具与 scan scope,写入 progress.json + audit_log
  -> 快速意图澄清(≤2问题,确保扫描准确性)
  -> dispatcher-agent 基线扫描(scan-of-record)
  -> 深度技术澄清(基于扫描结果)
  -> 复杂度路由 + 路由信号
  -> analyze -> design -> precheck -> audit
  -> RFC 输出
  -> 可选 /ohspec:export 生成机读件

语言要求

强制:所有交付物必须使用简体中文(RFC、findings.json、progress.json、审查报告)。

例外:代码标识符遵循项目约定。

快速开始

/ohspec "为音频服务增加 3D 音效开关"

Usage Examples

基础 RFC 生成

# 简单功能需求
/ohspec "为音频服务增加 3D 音效开关"

# 跨模块需求
/ohspec "实现用户认证模块与权限系统集成"

# 性能优化需求
/ohpec "优化数据库查询响应时间至 100ms 以内"

API 契约设计

# 设计新的 API 契约
/ohspec "设计用户注册 API 契约,包含邮箱验证和密码强度检查"

# 修改现有 API
/ohspec "重构支付接口,支持多种支付方式"

导出机读件

# 生成 RFC 后导出 digest 和 tasks
/ohspec "支付系统重构"

# 然后执行导出(手动触发)
/ohspec:export

# 输出:
# - rfc.digest.json (面向编码 Agent 的摘要)
# - tasks.json (可执行任务清单,支持 depends_on)

Resume 模式(中断恢复)

# 中断后恢复 RFC 生成
/ohspec:resume

# 列出所有 RFC
/ohspec:list

# 预检现有 RFC
/ohspec:precheck .ohspec/rfcs/RFC-20260126-example

Execution

核心执行流程

// OHSpec 核心执行流程(伪代码)
async function executeOHSpec(userRequirement, repoRoot) {
  // ============ 阶段 -1: 初始化三文件 ============
  const rfcId = generateRFCId();
  const rfcDir = `.ohspec/rfcs/${rfcId}`;

  await initializeThreeFiles(rfcDir, rfcId, userRequirement);
  // 产出:rfc.md(骨架)、findings.json(空结构)、progress.json(INIT 状态)

  // ============ 阶段 0: PRECHECK 需求预检 ============
  const precheckResult = await runRequirementPrecheck(userRequirement);
  await updateProgressJSON('requirement_precheck', precheckResult);

  if (!precheckResult.proceed) {
    return { error: '需求预检未通过', recommendations: precheckResult.recommendations };
  }

  // ============ 阶段 1: ASSESS 代码库评估(优化版) ============
  const assessResult = await runAssessOptimized(repoRoot, userRequirement);
  await updateProgressJSON('assess', assessResult);
  // 产出:tooling(搜索工具)、scan_scope、metrics(文件数/匹配数)

  // ============ 并行阶段:意图澄清 + 项目上下文加载 ============
  const [intentResult, contextData] = await Promise.all([
    runIntentClarify(userRequirement, assessResult),
    loadProjectContext(repoRoot)  // 可选,首次运行时执行
  ]);

  await updateProgressJSON('intent_clarify', intentResult);

  // ============ 阶段 3: dispatcher-agent 基线扫描(并行优化) ============
  const dispatcherResult = await runDispatcherParallel(
    userRequirement,
    intentResult,
    assessResult.tooling
  );

  // 合并结果到 findings.json
  await mergeFindings(dispatcherResult, contextData);
  // 产出:key_files(≥3,含角色标注)、facts(≥3,含证据锚点)

  // ============ 阶段 4: Gate-1 深度技术澄清 ============
  const gate1Result = await runTechnicalClarification(
    dispatcherResult,
    userRequirement
  );

  if (gate1Result.action === 'adjust_scope') {
    // 回到 dispatcher-agent 补扫
    await supplementScan(gate1Result.adjustments);
  }

  // ============ 阶段 5: 复杂度路由 ============
  const complexity = determineComplexity(dispatcherResult, intentResult);
  const signals = detectRoutingSignals(dispatcherResult, intentResult);

  // ============ 阶段 6: 执行对应流程 ============
  if (complexity === 'SIMPLE' || signals.includes('SKIP_ANALYZE')) {
    // 快速通道:分析 + 设计合并
    await runFastTrack(rfcId, dispatcherResult, userRequirement);
  } else if (complexity === 'MEDIUM') {
    // 标准流程
    await runStandardFlow(rfcId, dispatcherResult, userRequirement);
  } else {
    // COMPLEX:完整流程 + spike(如需)
    await runFullFlow(rfcId, dispatcherResult, userRequirement, signals);
  }

  // ============ 阶段 7: 质量门禁 ============
  const precheckResult = await runPrecheck(rfcDir);
  await updateProgressJSON('precheck', precheckResult);

  // ============ 阶段 8: 质量审查 ============
  const auditResult = await runAudit(rfcDir, precheckResult);
  await updateProgressJSON('audit', auditResult);

  return {
    rfcId,
    rfcPath: `${rfcDir}/rfc.md`,
    findingsPath: `${rfcDir}/findings.json`,
    progressPath: `${rfcDir}/progress.json`,
    complexity,
    signals,
    auditScore: auditResult.score
  };
}

关键优化函数

1. ASSESS 并行评估(优化版)

/**
 * ASSESS 阶段:并行评估代码库规模 + 缓存复用
 * 目标:30秒内完成,避免盲目扫描
 */
async function runAssessOptimized(repoRoot, userRequirement) {
  const startTime = Date.now();

  // 步骤 1: 检测搜索工具(并行检测多个)
  const searchTool = await detectSearchTool(['rg', 'ag', 'grep']);

  // 步骤 2: 并行统计文件数量 + 关键词预览
  const excludePatterns = [
    '**/.git/**', '**/.claude/**', '**/.ohspec/**',
    '**/node_modules/**', '**/dist/**', '**/build/**'
  ];

  const [fileCount, keywordMatches] = await Promise.all([
    countFiles(repoRoot, searchTool, excludePatterns),
    previewKeywords(repoRoot, extractKeywords(userRequirement), searchTool, excludePatterns)
  ]);

  // 步骤 3: 决策扫描策略
  const strategy = decideScanStrategy({
    totalFiles: fileCount,
    matchRatio: keywordMatches / fileCount,
    timeBudget: 30000 - (Date.now() - startTime)  // 保留时间给 dispatcher-agent
  });

  return {
    tooling: {
      search_tool: searchTool,
      fallback_used: searchTool === 'grep' ? 'true' : 'false',
      scan_scope: strategy.scope,
      strategy: strategy.mode
    },
    metrics: {
      total_files: fileCount,
      matched_files: keywordMatches,
      assessment_time_ms: Date.now() - startTime
    },
    strategy
  };
}

// 辅助:检测搜索工具(带回退)
async function detectSearchTool(preferences) {
  for (const tool of preferences) {
    const available = await checkToolAvailable(tool);
    if (available) return tool;
  }
  return 'grep';  // 最后回退
}

2. dispatcher-agent 并行扫描

/**
 * dispatcher-agent 基线扫描:并行子任务优化
 * 目标:快速收集 key_files + facts,避免串行等待
 */
async function runDispatcherParallel(requirement, intentContext, tooling) {
  // 子任务 1: 扫描入口文件
  const taskEntries = scanEntries(requirement, tooling);

  // 子任务 2: 扫描配置文件
  const taskConfig = scanConfig(requirement, tooling);

  // 子任务 3: 扫描依赖声明
  const taskDeps = scanDependencies(requirement, tooling);

  // 子任务 4: 扫描测试/可观测(可选)
  const taskTests = scanTests(requirement, tooling);

  // 并行执行所有子任务
  const [entries, config, deps, tests] = await Promise.all([
    taskEntries,
    taskConfig,
    taskDeps,
    taskTests.catch(() => ({ files: [], facts: [] }))  // 失败不阻断
  ]);

  // 合并结果
  const keyFiles = [
    ...entries.files,
    ...config.files,
    ...deps.files,
    ...tests.files
  ].filter(distinct);

  const facts = [
    ...entries.facts,
    ...config.facts,
    ...deps.facts,
    ...tests.facts
  ].filter(distinct);

  return {
    complexity: estimateComplexity(keyFiles, facts),
    intent: intentContext.primary_intent,
    scope: {
      key_files: keyFiles.slice(0, 10),  // 限制数量
      dependencies: deps.files,
      config_files: config.files
    },
    findings: {
      confirmed: {
        key_files: keyFiles,
        facts: facts
      }
    },
    signals: detectRoutingSignals(keyFiles, facts)
  };
}

3. 复杂度路由

/**
 * 复杂度路由:基于扫描结果动态选择执行路径
 */
function determineComplexity(dispatcherResult, intentContext) {
  const { key_files, facts } = dispatcherResult.findings.confirmed;
  const fileCount = key_files.length;
  const factCount = facts.length;

  // SIMPLE: 单文件,<50行
  if (fileCount <= 2 && factCount >= 1 && !intentContext.cross_module) {
    return 'SIMPLE';
  }

  // COMPLEX: 跨子系统,>200行或架构级
  if (fileCount >= 10 || intentContext.cross_module || intentContext.architecture_level) {
    return 'COMPLEX';
  }

  // MEDIUM: 默认
  return 'MEDIUM';
}

/**
 * 路由信号检测:动态调整执行路径
 */
function detectRoutingSignals(keyFiles, facts, intentContext) {
  const signals = [];

  // SKIP_ANALYZE: 需求明确、单文件影响
  if (keyFiles.length <= 2 && intentContext.user_provided_detail) {
    signals.push('SKIP_ANALYZE');
  }

  // LOAD_DIPLOMAT: 跨子系统依赖
  if (facts.some(f => f.category === 'cross_subsystem')) {
    signals.push('LOAD_DIPLOMAT');
  }

  // TRIGGER_SPIKE: 技术不确定
  if (facts.some(f => f.uncertainty === 'high')) {
    signals.push('TRIGGER_SPIKE');
  }

  // SIMPLIFY_CLARIFY: 详细需求
  if (intentContext.information_score >= 85) {
    signals.push('SIMPLIFY_CLARIFY');
  }

  return signals;
}

执行模式对比

┌─ 串行模式(默认) ─────────────────────────────────────┐
│ PRECHECK → ASSESS → 意图澄清 → dispatcher → Gate-1 →  │
│ analyze → Gate-2 → design → precheck → audit          │
│ 预计耗时:~5-8 分钟                                     │
└────────────────────────────────────────────────────────┘

┌─ 并行模式(优化) ─────────────────────────────────────┐
│ PRECHECK → ASSESS(并行统计)                          │
│   ↓                                                      │
│ [意图澄清 || 项目上下文加载]  (并行,~30s 节省)         │
│   ↓                                                      │
│ dispatcher(并行子任务:入口+配置+依赖+测试)            │
│   ↓                                                      │
│ Gate-1 → [快速通道 || 标准流程 || 完整流程]              │
│   ↓                                                      │
│ precheck + audit(自动流转)                             │
│ 预计耗时:~3-5 分钟(提升 40-60%)                       │
└────────────────────────────────────────────────────────┘

关键优化收益

| 优化项 | 收益 | 适用场景 | |--------|------|----------| | ASSESS 并行统计 | 节省 10-15s | 所有任务 | | 意图澄清 + 上下文并行 | 节省 20-30s | 首次运行 | | dispatcher 并行扫描 | 节省 30-60s | MEDIUM/COMPLEX | | 快速通道(SIMPLE) | 节省 2-3 分钟 | 单文件任务 | | SKIP_ANALYZE 信号 | 节省 1-2 分钟 | 需求明确 | | 自动流转 | 减少用户等待 | 无需决策阶段 |

Agent 选择

| Agent | 用途 | |-------|------| | dispatcher-agent | 基线扫描(scan-of-record) | | analyze-agent | 深度技术澄清,输出 RFC §1-§2 | | design-agent | 设计方案,定义接口,输出 RFC §3-§5 | | api-design-agent | API 契约设计与验证 | | diplomat-agent | 跨子系统依赖处理 | | prototyper-agent | Spike 验证(技术不确定) | | audit-agent | 质量审查,评分决策 |

质量门禁

必须满足

  • 5 个 RFC 章节完整
  • 8 个 DFX 维度量化
  • 4 种场景类型覆盖(Gherkin格式)
  • 无模糊描述

RFC 格式

ID格式RFC-{YYYYMMDD}-{slug}-{hash4}

目录(推荐).ohspec/rfcs/{RFC-ID}/ 兼容(历史).claude/ohspec/rfcs/{RFC-ID}/

Reference Documents

必读文档(P0)

参考文档(按需)

  • 其他工作流: phases/ - precheck, export, resume, spike 等
  • 其他文档: docs/ - routing-signals, implementation-guide, best-practices, error-handling
  • 扩展模板: templates/ - rfc-minimal, project-context, checkpoint 等

Scripts 目录

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB OPENCLEW

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/snapshot"
curl -s "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/contract"
curl -s "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
GITHUB_REPOSactivepieces

Rank

70

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Traction

No public download signal

Freshness

Updated 2d ago

OPENCLAW
GITHUB_REPOScherry-studio

Rank

70

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Traction

No public download signal

Freshness

Updated 5d ago

MCPOPENCLAW
GITHUB_REPOSAionUi

Rank

70

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW
GITHUB_REPOSCopilotKit

Rank

70

The Frontend for Agents & Generative UI. React + Angular

Traction

No public download signal

Freshness

Updated 23d ago

OPENCLAW
Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/clipsheep6-ohspec/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clipsheep6-ohspec/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clipsheep6-ohspec/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-16T23:32:50.654Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "scope",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:scope|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Clipsheep6",
    "href": "https://github.com/clipsheep6/ohspec",
    "sourceUrl": "https://github.com/clipsheep6/ohspec",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T03:13:56.426Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T03:13:56.426Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clipsheep6-ohspec/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to ohspec and adjacent AI workflows.