MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Lightweight execution engine - multi-mode input, task grouping, batch execution, chain to workflow-lite-test-review
$ npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install catlog22/Claude-Code-Workflow workflow-lite-execute --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/workflow-lite-execute .claude/skills/workflow-lite-execute && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "workflow-lite-execute" agent skill from https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/workflow-lite-execute into .claude/skills/workflow-lite-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-lite-execute", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/workflow-lite-executeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install catlog22/Claude-Code-Workflow workflow-lite-execute --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/workflow-lite-execute .agents/skills/workflow-lite-execute && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "workflow-lite-execute" agent skill from https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/workflow-lite-execute into .agents/skills/workflow-lite-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-lite-execute", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install catlog22/Claude-Code-Workflow workflow-lite-execute --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/workflow-lite-execute .cursor/skills/workflow-lite-execute && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "workflow-lite-execute" agent skill from https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/workflow-lite-execute into .cursor/skills/workflow-lite-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-lite-execute", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/catlog22/Claude-Code-Workflow.git --path .claude/skills/workflow-lite-execute--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install catlog22/Claude-Code-Workflow workflow-lite-execute --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/workflow-lite-execute .gemini/skills/workflow-lite-execute && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "workflow-lite-execute" agent skill from https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/workflow-lite-execute into .gemini/skills/workflow-lite-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-lite-execute", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install catlog22/Claude-Code-Workflow workflow-lite-executeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/workflow-lite-execute .github/skills/workflow-lite-execute && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "workflow-lite-execute" agent skill from https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/workflow-lite-execute into .github/skills/workflow-lite-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-lite-execute", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install catlog22/Claude-Code-Workflow workflow-lite-execute --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/workflow-lite-execute .opencode/skills/workflow-lite-execute && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "workflow-lite-execute" agent skill from https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/workflow-lite-execute into .opencode/skills/workflow-lite-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-lite-execute", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
workflow-lite-executeLightweight execution engine - multi-mode input, task grouping, batch execution, chain to workflow-lite-test-review
Workflow Lite Execute is an agent skill from catlog22/Claude-Code-Workflow. Lightweight execution engine - multi-mode input, task grouping, batch execution, chain to workflow-lite-test-review
Its SKILL.md is about 5.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. The repository describes itself as: JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 07491b0. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
SkillAgentAskUserQuestionTodoWriteReadWriteEditBashGlobGrepFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Workflow Lite Execute loads about 5.6k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 460 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Skill, Agent, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob, GrepAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from catlog22/Claude-Code-Workflow at commit 07491b0, republished under its MIT licence (© catlog22). 460 words, ~5,638 tokens.
.claude/skills/workflow-lite-execute/SKILL.md (or your agent's skills folder).Execution engine for workflow-lite-plan handoff and standalone task execution.
<input> Task description string, or path to file (required)| Flag | Description |
|---|---|
--in-memory | Mode 1: Use executionContext from workflow-lite-plan handoff (via Skill({ skill: "workflow-lite-execute", args: "--in-memory" }) |
Trigger: --in-memory flag or executionContext global variable available
Input Source: executionContext global variable set by workflow-lite-plan
Behavior: Skip execution method/code review selection (already chosen in LP-Phase 4), directly proceed with full context (exploration, clarifications, plan artifacts all available)
Note: LP-Phase 4 is the single confirmation gate. Mode 1 invocation means user already approved — no further prompts.
Trigger: User calls with task description string (e.g., "Add unit tests for auth module")
Behavior: Store prompt as originalUserInput → create simple execution plan → run selectExecutionOptions() → proceed
Trigger: User calls with file path (ends with .md/.json/.txt)
fileContent = Read(filePath)
try {
jsonData = JSON.parse(fileContent)
// plan.json detection: two-layer format with task_ids[]
if (jsonData.summary && jsonData.approach && jsonData.task_ids) {
planObject = jsonData
originalUserInput = jsonData.summary
isPlanJson = true
const planDir = filePath.replace(/[/\\][^/\\]+$/, '')
planObject._loadedTasks = loadTaskFiles(planDir, jsonData.task_ids)
} else {
originalUserInput = fileContent
isPlanJson = false
}
} catch {
originalUserInput = fileContent
isPlanJson = false
}isPlanJson === true: Use planObject directly → run selectExecutionOptions()isPlanJson === false: Treat as prompt (same as Mode 2)function selectExecutionOptions() {
// autoYes: set by -y flag (standalone only; Mode 1 never reaches here)
const autoYes = workflowPreferences?.autoYes ?? false
if (autoYes) {
return { execution_method: "Auto", code_review_tool: "Skip", convergence_review_tool: "Skip" }
}
return AskUserQuestion({
questions: [
{
question: "Select execution method:",
header: "Execution",
multiSelect: false,
options: [
{ label: "Agent", description: "@code-developer agent" },
{ label: "Codex", description: "codex CLI tool" },
{ label: "Auto", description: "Auto-select based on complexity" }
]
},
{
question: "Code review after execution? (runs here in lite-execute)",
header: "Code Review",
multiSelect: false,
options: [
{ label: "Gemini Review", description: "Gemini CLI: git diff quality review" },
{ label: "Codex Review", description: "Codex CLI: prompt-based code quality review (--mode analysis)" },
{ label: "Agent Review", description: "@code-reviewer agent" },
{ label: "Skip", description: "No code review" }
]
},
{
question: "Convergence review in workflow-lite-test-review phase?",
header: "Convergence Review",
multiSelect: false,
options: [
{ label: "Agent", description: "Agent: verify convergence criteria" },
{ label: "Gemini", description: "Gemini CLI: convergence verification" },
{ label: "Codex", description: "Codex CLI: convergence verification" },
{ label: "Skip", description: "Skip convergence review, run tests only" }
]
}
]
})
}previousExecutionResults = []
// Mode 1: echo strategy for transparency
if (executionContext) {
console.log(`
Execution Strategy (from lite-plan):
Method: ${executionContext.executionMethod}
Code Review: ${executionContext.codeReviewTool}
Convergence Review: ${executionContext.convergenceReviewTool}
Tasks: ${getTasks(executionContext.planObject).length}
Complexity: ${executionContext.planObject.complexity}
${executionContext.executorAssignments ? ` Assignments: ${JSON.stringify(executionContext.executorAssignments)}` : ''}
`)
}
// Helper: load .task/*.json files (two-layer format)
function loadTaskFiles(planDir, taskIds) {
return taskIds.map(id => JSON.parse(Read(`${planDir}/.task/${id}.json`)))
}
function getTasks(planObject) {
return planObject._loadedTasks || []
}// Dependency extraction: explicit depends_on only (no file/keyword inference)
function extractDependencies(tasks) {
const taskIdToIndex = {}
tasks.forEach((t, i) => { taskIdToIndex[t.id] = i })
return tasks.map((task, i) => {
const deps = (task.depends_on || [])
.map(depId => taskIdToIndex[depId])
.filter(idx => idx !== undefined && idx < i)
return { ...task, taskIndex: i, dependencies: deps }
})
}
// Executor resolution: executorAssignments[taskId] > executionMethod > Auto fallback
function getTaskExecutor(task) {
const assignments = executionContext?.executorAssignments || {}
if (assignments[task.id]) return assignments[task.id].executor // 'gemini' | 'codex' | 'agent'
const method = executionContext?.executionMethod || 'Auto'
if (method === 'Agent') return 'agent'
if (method === 'Codex') return 'codex'
return planObject.complexity === 'Low' ? 'agent' : 'codex' // Auto fallback
}
function groupTasksByExecutor(tasks) {
const groups = { gemini: [], codex: [], agent: [] }
tasks.forEach(task => { groups[getTaskExecutor(task)].push(task) })
return groups
}
// Batch creation: independent → per-executor parallel, dependent → sequential phases
function createExecutionCalls(tasks, executionMethod) {
const tasksWithDeps = extractDependencies(tasks)
const processed = new Set()
const calls = []
// Phase 1: Independent tasks → per-executor parallel batches
const independentTasks = tasksWithDeps.filter(t => t.dependencies.length === 0)
if (independentTasks.length > 0) {
const executorGroups = groupTasksByExecutor(independentTasks)
let parallelIndex = 1
for (const [executor, tasks] of Object.entries(executorGroups)) {
if (tasks.length === 0) continue
tasks.forEach(t => processed.add(t.taskIndex))
calls.push({
method: executionMethod, executor, executionType: "parallel",
groupId: `P${parallelIndex++}`,
taskSummary: tasks.map(t => t.title).join(' | '), tasks
})
}
}
// Phase 2+: Dependent tasks → respect dependency order
let sequentialIndex = 1
let remaining = tasksWithDeps.filter(t => !processed.has(t.taskIndex))
while (remaining.length > 0) {
let ready = remaining.filter(t => t.dependencies.every(d => processed.has(d)))
if (ready.length === 0) { console.warn('Circular dependency detected, forcing remaining'); ready = [...remaining] }
if (ready.length > 1) {
const executorGroups = groupTasksByExecutor(ready)
for (const [executor, tasks] of Object.entries(executorGroups)) {
if (tasks.length === 0) continue
tasks.forEach(t => processed.add(t.taskIndex))
calls.push({
method: executionMethod, executor, executionType: "parallel",
groupId: `P${calls.length + 1}`,
taskSummary: tasks.map(t => t.title).join(' | '), tasks
})
}
} else {
ready.forEach(t => processed.add(t.taskIndex))
calls.push({
method: executionMethod, executor: getTaskExecutor(ready[0]),
executionType: "sequential", groupId: `S${sequentialIndex++}`,
taskSummary: ready[0].title, tasks: ready
})
}
remaining = remaining.filter(t => !processed.has(t.taskIndex))
}
return calls
}
executionCalls = createExecutionCalls(getTasks(planObject), executionMethod).map(c => ({ ...c, id: `[${c.groupId}]` }))
TodoWrite({
todos: executionCalls.map((c, i) => ({
content: `${c.executionType === "parallel" ? "⚡" : `→ [${i+1}/${executionCalls.filter(x=>x.executionType==="sequential").length}]`} ${c.id} [${c.executor}] ${c.tasks.map(t=>t.id).join(', ')}`,
status: "pending",
activeForm: `Waiting: ${c.tasks.length} task(s) via ${c.executor}`
}))
})CHECKPOINT: Verify Phase 2 execution protocol (Step 3-5) is in active memory. If only a summary remains, re-read
phases/02-lite-execute.mdnow.
Batch Routing (by batch.executor field):
function executeBatch(batch) {
const executor = batch.executor || getTaskExecutor(batch.tasks[0])
const sessionId = executionContext?.session?.id || 'standalone'
const fixedId = `${sessionId}-${batch.groupId}`
if (executor === 'agent') {
return Agent({ subagent_type: "code-developer", run_in_background: false,
description: batch.taskSummary, prompt: buildExecutionPrompt(batch) })
} else {
// CLI execution (codex/gemini): background with fixed ID
const tool = executor // 'codex' | 'gemini'
const mode = executor === 'gemini' ? 'analysis' : 'write'
const previousCliId = batch.resumeFromCliId || null
const cmd = previousCliId
? `ccw cli -p "${buildExecutionPrompt(batch)}" --tool ${tool} --mode ${mode} --id ${fixedId} --resume ${previousCliId}`
: `ccw cli -p "${buildExecutionPrompt(batch)}" --tool ${tool} --mode ${mode} --id ${fixedId}`
return Bash(cmd, { run_in_background: true })
// STOP - wait for task hook callback
}
}Parallel execution rules:
Execution Flow: Parallel batches concurrently → Sequential batches in order
const parallel = executionCalls.filter(c => c.executionType === "parallel")
const sequential = executionCalls.filter(c => c.executionType === "sequential")
// Phase 1: All parallel batches (single message, multiple tool calls)
if (parallel.length > 0) {
TodoWrite({ todos: executionCalls.map(c => ({
status: c.executionType === "parallel" ? "in_progress" : "pending",
activeForm: c.executionType === "parallel" ? `Running [${c.executor}]: ${c.tasks.map(t=>t.id).join(', ')}` : `Blocked by parallel phase`
})) })
parallelResults = await Promise.all(parallel.map(c => executeBatch(c)))
previousExecutionResults.push(...parallelResults)
TodoWrite({ todos: executionCalls.map(c => ({
status: parallel.includes(c) ? "completed" : "pending",
activeForm: parallel.includes(c) ? `Done [${c.executor}]` : `Ready`
})) })
}
// Phase 2: Sequential batches one by one
for (const call of sequential) {
TodoWrite({ todos: executionCalls.map(c => ({
status: c === call ? "in_progress" : (c.status === "completed" ? "completed" : "pending"),
activeForm: c === call ? `Running [${c.executor}]: ${c.tasks.map(t=>t.id).join(', ')}` : undefined
})) })
result = await executeBatch(call)
previousExecutionResults.push(result)
TodoWrite({ todos: executionCalls.map(c => ({
status: sequential.indexOf(c) <= sequential.indexOf(call) ? "completed" : "pending"
})) })
}Resume on Failure:
if (bash_result.status === 'failed' || bash_result.status === 'timeout') {
// fixedId = `${sessionId}-${groupId}` (predictable, no auto-generated timestamps)
console.log(`Execution incomplete. Resume: ccw cli -p "Continue" --resume ${fixedId} --tool codex --mode write --id ${fixedId}-retry`)
batch.resumeFromCliId = fixedId
}Progress tracked at batch level. Icons: ⚡ parallel (concurrent), → sequential (one-by-one).
Each task is a self-contained checklist. Same template for Agent and CLI.
function buildExecutionPrompt(batch) {
const formatTask = (t) => `
## ${t.title}
**Scope**: \`${t.scope}\` | **Action**: ${t.action}
### Files
${(t.files || []).map(f => `- **${f.path}** → \`${f.target || ''}\`: ${f.change || (f.changes || []).join(', ') || ''}`).join('\n')}
${t.rationale ? `### Why this approach (Medium/High)
${t.rationale.chosen_approach}
${t.rationale.decision_factors?.length > 0 ? `Key factors: ${t.rationale.decision_factors.join(', ')}` : ''}
${t.rationale.tradeoffs ? `Tradeoffs: ${t.rationale.tradeoffs}` : ''}` : ''}
### How to do it
${t.description}
${t.implementation.map(step => `- ${step}`).join('\n')}
${t.code_skeleton ? `### Code skeleton (High)
${t.code_skeleton.interfaces?.length > 0 ? `**Interfaces**: ${t.code_skeleton.interfaces.map(i => `\`${i.name}\` - ${i.purpose}`).join(', ')}` : ''}
${t.code_skeleton.key_functions?.length > 0 ? `**Functions**: ${t.code_skeleton.key_functions.map(f => `\`${f.signature}\` - ${f.purpose}`).join(', ')}` : ''}
${t.code_skeleton.classes?.length > 0 ? `**Classes**: ${t.code_skeleton.classes.map(c => `\`${c.name}\` - ${c.purpose}`).join(', ')}` : ''}` : ''}
### Reference
- Pattern: ${t.reference?.pattern || 'N/A'}
- Files: ${t.reference?.files?.join(', ') || 'N/A'}
${t.reference?.examples ? `- Notes: ${t.reference.examples}` : ''}
${t.risks?.length > 0 ? `### Risk mitigations (High)
${t.risks.map(r => `- ${r.description} → **${r.mitigation}**`).join('\n')}` : ''}
### Done when
${(t.convergence?.criteria || []).map(c => `- [ ] ${c}`).join('\n')}
${(t.test?.success_metrics || []).length > 0 ? `**Success metrics**: ${t.test.success_metrics.join(', ')}` : ''}`
const sections = []
if (originalUserInput) sections.push(`## Goal\n${originalUserInput}`)
sections.push(`## Tasks\n${batch.tasks.map(formatTask).join('\n\n---\n')}`)
const context = []
if (previousExecutionResults.length > 0)
context.push(`### Previous Work\n${previousExecutionResults.map(r => `- ${r.tasksSummary}: ${r.status}`).join('\n')}`)
if (clarificationContext)
context.push(`### Clarifications\n${Object.entries(clarificationContext).map(([q, a]) => `- ${q}: ${a}`).join('\n')}`)
if (executionContext?.planObject?.data_flow?.diagram)
context.push(`### Data Flow\n${executionContext.planObject.data_flow.diagram}`)
if (executionContext?.session?.artifacts?.plan)
context.push(`### Artifacts\nPlan: ${executionContext.session.artifacts.plan}`)
context.push(`### Project Guidelines\n(Loaded via ccw spec load --category planning)`)
if (context.length > 0) sections.push(`## Context\n${context.join('\n\n')}`)
sections.push(`Complete each task according to its "Done when" checklist.`)
return sections.join('\n\n')
}Skip if: codeReviewTool === 'Skip'
Resolve review tool: From executionContext.codeReviewTool (Mode 1) or userSelection.code_review_tool (Mode 2/3).
const codeReviewTool = executionContext?.codeReviewTool || userSelection?.code_review_tool || 'Skip'
const resolvedTool = (() => {
if (!codeReviewTool || codeReviewTool === 'Skip') return 'skip'
if (/gemini/i.test(codeReviewTool)) return 'gemini'
if (/codex/i.test(codeReviewTool)) return 'codex'
return 'agent'
})()
if (resolvedTool === 'skip') {
console.log('[Code Review] Skipped')
} else {
// proceed with review
}Agent Code Review (resolvedTool === 'agent'):
Agent({
subagent_type: "code-reviewer",
run_in_background: false,
description: `Code review: ${planObject.summary}`,
prompt: `## Code Review — Post-Execution Quality Check
**Goal**: ${originalUserInput}
**Plan Summary**: ${planObject.summary}
### Changed Files
Run \`git diff --name-only HEAD~${getTasks(planObject).length}..HEAD\` to identify changes.
### Review Focus
1. **Code quality**: Readability, naming, structure, dead code
2. **Correctness**: Logic errors, off-by-one, null handling, edge cases
3. **Patterns**: Consistency with existing codebase conventions
4. **Security**: Injection, XSS, auth bypass, secrets exposure
5. **Performance**: Unnecessary loops, N+1 queries, missing indexes
### Instructions
1. Run git diff to see actual changes
2. Read changed files for full context
3. For each issue found: severity (Critical/High/Medium/Low) + file:line + description + fix suggestion
4. Return structured review: issues[], summary, overall verdict (PASS/WARN/FAIL)`
})CLI Code Review — Codex (resolvedTool === 'codex'):
const reviewId = `${sessionId}-code-review`
Bash(`ccw cli -p "PURPOSE: Post-execution code quality review for: ${planObject.summary}
TASK: • Run git diff to identify all changes • Review each changed file for quality, correctness, security • Check pattern compliance with existing codebase • Identify potential bugs, edge cases, performance issues
MODE: analysis
CONTEXT: @**/* | Memory: lite-execute completed, reviewing code quality
EXPECTED: Per-file review with severity levels (Critical/High/Medium/Low), file:line references, fix suggestions, overall verdict
CONSTRAINTS: Read-only | Focus on code quality not convergence" --tool codex --mode analysis --rule analysis-review-code-quality --id ${reviewId}`, { run_in_background: true })
// STOP - wait for hook callbackCLI Code Review — Gemini (resolvedTool === 'gemini'):
const reviewId = `${sessionId}-code-review`
Bash(`ccw cli -p "PURPOSE: Post-execution code quality review for: ${planObject.summary}
TASK: • Run git diff to identify all changes • Review each changed file for quality, correctness, security • Check pattern compliance with existing codebase • Identify potential bugs, edge cases, performance issues
MODE: analysis
CONTEXT: @**/* | Memory: lite-execute completed, reviewing code quality
EXPECTED: Per-file review with severity levels (Critical/High/Medium/Low), file:line references, fix suggestions, overall verdict
CONSTRAINTS: Read-only | Focus on code quality not convergence" --tool gemini --mode analysis --rule analysis-review-code-quality --id ${reviewId}`, { run_in_background: true })
// STOP - wait for hook callbackWrite review artifact (if session folder exists):
if (executionContext?.session?.folder) {
Write(`${executionContext.session.folder}/code-review.md`, codeReviewOutput)
}Resolve convergence review tool: From executionContext.convergenceReviewTool (Mode 1) or userSelection.convergence_review_tool (Mode 2/3).
function resolveConvergenceTool(ctx, selection) {
const raw = ctx?.convergenceReviewTool || selection?.convergence_review_tool || 'skip'
if (!raw || raw === 'Skip') return 'skip'
if (/gemini/i.test(raw)) return 'gemini'
if (/codex/i.test(raw)) return 'codex'
return 'agent'
}Build testReviewContext and handoff:
testReviewContext = {
planObject: planObject,
taskFiles: executionContext?.taskFiles
|| getTasks(planObject).map(t => ({ id: t.id, path: `${executionContext?.session?.folder}/.task/${t.id}.json` })),
convergenceReviewTool: resolveConvergenceTool(executionContext, userSelection),
executionResults: previousExecutionResults,
originalUserInput: originalUserInput,
session: executionContext?.session || {
id: 'standalone',
folder: executionContext?.session?.folder || '.',
artifacts: { plan: null, task_dir: null }
}
}
// Chain to workflow-lite-test-review (Mode 1: In-Memory)
Skill("workflow-lite-test-review")
// testReviewContext passed as global variableAfter workflow-lite-test-review returns: Ask user whether to expand into issues (enhance/refactor/doc). Selected items call /issue:new "{summary} - {dimension}".
| Error | Resolution |
|---|---|
| Missing executionContext | "No execution context found. Only available when called by lite-plan." |
| File not found | "File not found: {path}. Check file path." |
| Empty file | "File is empty: {path}. Provide task description." |
| Invalid plan JSON | Warning: "Missing required fields. Treating as plain text." |
| Malformed JSON | Treat as plain text (expected for non-JSON files) |
| Execution failure | Use fixed ID ${sessionId}-${groupId} for resume |
| Execution timeout | Use fixed ID for resume with extended timeout |
| Codex unavailable | Show installation instructions, offer Agent execution |
| Fixed ID not found | Check ccw cli history, verify date directories |
{
planObject: {
summary: string,
approach: string,
task_ids: string[],
task_count: number,
_loadedTasks: [...], // populated at runtime from .task/*.json
estimated_time: string,
recommended_execution: string,
complexity: string
},
taskFiles: [{id: string, path: string}] | null,
explorationsContext: {...} | null,
explorationAngles: string[],
explorationManifest: {...} | null,
clarificationContext: {...} | null,
executionMethod: "Agent" | "Codex" | "Auto",
codeReviewTool: "Skip" | "Gemini Review" | "Codex Review" | "Agent Review",
convergenceReviewTool: "Skip" | "Agent" | "Gemini" | "Codex",
originalUserInput: string,
executorAssignments: { // per-task override, priority over executionMethod
[taskId]: { executor: "gemini" | "codex" | "agent", reason: string }
},
session: {
id: string, // {taskSlug}-{shortTimestamp}
folder: string, // .workflow/.lite-plan/{session-id}
artifacts: {
explorations: [{angle, path}],
explorations_manifest: string,
plan: string // always present
}
}
}{
executionId: string, // e.g., "[Agent-1]", "[Codex-1]"
status: "completed" | "partial" | "failed",
tasksSummary: string,
completionSummary: string,
keyOutputs: string,
notes: string,
fixedCliId: string | null // for resume: ccw cli detail ${fixedCliId}
}
// Appended to previousExecutionResults[] for context continuity© catlog22, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/workflow-lite-execute of catlog22/Claude-Code-Workflow.
Open the folder on GitHubat commit 07491b0
Workflow Lite Execute next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Workflow Lite Execute this skillcatlog22/Claude-Code-Workflow | 2.1k | — | ~5.6k | Automated safety check: Notes | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
catlog22/Claude-Code-Workflow
Generate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conversion of existing files.
catlog22/Claude-Code-Workflow
CCW command help system. An agent skill from catlog22/Claude-Code-Workflow.
catlog22/Claude-Code-Workflow
Deep collaborative analysis team skill. An agent skill from catlog22/Claude-Code-Workflow.
catlog22/Claude-Code-Workflow
Unified brainstorming skill with dual-mode operation — auto mode (framework generation, parallel multi-role analysis, cross-role synthesis) and single role analysis.
catlog22/Claude-Code-Workflow
Chain-based CCW workflow orchestrator. An agent skill from catlog22/Claude-Code-Workflow.
catlog22/Claude-Code-Workflow
Check workflow delegation prompts against agent role definitions for content separation violations.
Categories
Lightweight execution engine - multi-mode input, task grouping, batch execution, chain to workflow-lite-test-review. Workflow Lite Execute is an agent skill from catlog22/Claude-Code-Workflow.
Workflow Lite Execute fits situations like: agent Workflows work in your project.
Run `npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a claude-code`. Or copy the skill folder (.claude/skills/workflow-lite-execute in catlog22/Claude-Code-Workflow) into .claude/skills/workflow-lite-execute in your project. Claude Code loads it when a task matches its description.
Run `npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a codex`. Or copy the skill folder (.claude/skills/workflow-lite-execute in catlog22/Claude-Code-Workflow) into .agents/skills/workflow-lite-execute in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add catlog22/Claude-Code-Workflow --skill workflow-lite-execute -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/workflow-lite-execute, .gemini/skills/workflow-lite-execute, .github/skills/workflow-lite-execute and .opencode/skills/workflow-lite-execute in your project.
SKILL.md names no scripts, command-line tools or credentials: Workflow Lite Execute is instructions for the agent only. Its frontmatter pre-approves these tools: Skill, Agent, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob, Grep.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Workflow Lite Execute is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.6k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Workflow Lite Execute: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
catlog22 (a GitHub user) maintains it in catlog22/Claude-Code-Workflow, which has 2,130 GitHub stars. The repository holds 82 skills in this directory. The repository was last updated on June 18, 2026.
Source: catlog22/Claude-Code-Workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.