@cubis/foundry 0.3.64 → 0.3.66

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/postman/SKILL.md

@@ -0,0 +1,126 @@
+---
+name: postman
+description: Automate API testing and collection management with Postman MCP using full-mode defaults and workspace-aware execution.
+---
+
+# Postman MCP Skill
+
+Use this skill when you need Postman workspace, collection, environment, or run operations through MCP.
+
+References:
+- [Full-Mode Setup](./references/full-mode-setup.md)
+- [Workspace Policy](./references/workspace-policy.md)
+- [Troubleshooting](./references/troubleshooting.md)
+
+## MCP-First Rule
+
+- Prefer Postman MCP tools for all Postman operations.
+- Use direct Postman server tools for actual Postman cloud work:
+  - direct server: `postman.<tool>`
+  - client-wrapped direct server: `mcp__postman__<tool>`
+- Treat Foundry `postman_*` tools as config helpers only:
+  - `postman_get_status`
+  - `postman_get_mode`
+  - `postman_set_mode`
+- Never default to raw Postman REST JSON payloads, Newman, or Postman CLI when MCP tools are available.
+- Do not use `postman.runMonitor` as an automatic fallback after `postman.runCollection` timeout or failure.
+- Only use monitor execution when the user explicitly asks for monitor-based cloud execution, scheduled monitoring, or monitor validation.
+- Recommend Postman CLI as the default secondary path when direct MCP execution fails.
+- If required Postman MCP tools are unavailable, report discovery/remediation steps first.
+
+## Setup Baseline
+
+1. Install with Postman enabled and explicit full mode (use the same scope as your current install):
+   - `cbx workflows install --platform <codex|antigravity|copilot> --scope <project|global> --bundle agent-environment-setup --postman --postman-mode full --mcp-runtime docker --mcp-fallback local --mcp-tool-sync --yes`
+2. Persist env aliases once (no per-session re-export):
+   - `cbx workflows config keys persist-env --service postman --scope global`
+3. Verify mode/config:
+   - `cbx workflows config --scope <project|global> --show`
+   - `cbx mcp tools sync --service postman --scope <project|global>`
+   - `cbx mcp tools list --service postman --scope <project|global>`
+
+## Preflight
+
+1. Read Postman status first:
+   - Call `postman_get_status` for mode/default-workspace/config state.
+2. Ensure mode is `full`:
+   - If not, call `postman_set_mode` with `mode: full`.
+3. Discover upstream tools:
+   - Confirm required direct Postman server tools exist before execution (for example workspaces/collections/runs).
+
+Execution rule:
+- For Postman requests, call the direct Postman server (`postman.<tool>` or `mcp__postman__<tool>`) instead of Foundry `postman_*` config tools.
+- If the user asks for API payload examples, provide them only as supplemental documentation after MCP execution guidance.
+
+Quota-safe rule:
+- If `postman.runCollection` times out or fails, stop and classify the error before choosing any fallback.
+- Never auto-convert a collection run failure into `postman.runMonitor`.
+- Recommend Postman CLI first for repeatable local reruns.
+
+## Default Workspace Policy
+
+Resolve workspace in this order:
+
+1. User-provided workspace ID.
+2. `postman_get_status.defaultWorkspaceId`.
+3. Auto-detect from workspace listing:
+   - If exactly one workspace exists, use it and state that choice.
+4. If multiple workspaces and no default:
+   - Ask user to choose one.
+   - Recommend persisting it with:
+     - `cbx workflows config --scope <project|global> --workspace-id <workspace-id>`
+
+When a Postman tool requires a workspace argument, always pass the resolved workspace ID explicitly.
+
+## Common Workflows
+
+### Collection Run
+
+1. Resolve workspace ID (policy above).
+2. Resolve `collectionId` and optional `environmentId`.
+3. Call Postman run tool (`postman.runCollection` or alias equivalent).
+4. Return a concise run summary:
+   - total requests
+   - passed/failed tests
+   - failing request/test names
+   - proposed fix path for failures
+
+## Failure Handling
+
+### Error Classification
+
+Classify failures before suggesting any fallback:
+
+- `limitBreachedError` or "breached monitoring usage limit":
+  - monitor quota exhaustion
+  - do not retry monitor runs
+  - recommend local Postman CLI execution
+  - tell the user to check the Postman monitoring usage dashboard
+- `429` or rate-limit response:
+  - Postman API rate limiting
+  - recommend backoff and a lower request burst
+  - do not reinterpret it as monitor quota
+- collection run timeout without quota/rate-limit signal:
+  - direct MCP runtime or tool timeout
+  - do not auto-convert to a monitor run
+  - recommend Postman CLI or a smaller-scope rerun
+
+### Quota Notes
+
+- Monitor usage is separate from Postman API rate limits.
+- Monitor usage is plan/billing usage and is consumed by request count, region count, and auth requests.
+- Monitor runtime caps are separate from monitor quota and do not imply quota remains available.
+
+If dynamic Postman tools are missing:
+
+1. Verify env alias expected by config is set.
+2. Resync catalog:
+   - `cbx mcp tools sync --service postman --scope <project|global>`
+   - `cbx mcp tools list --service postman --scope <project|global>`
+3. Recreate runtime if needed:
+   - `cbx mcp runtime up --scope <project|global> --name cbx-mcp --replace --port 3310 --skills-root ~/.agents/skills`
+
+## Security Notes
+
+- Use environment variables for secrets. Do not inline API keys.
+- Never print or persist raw key values in logs, docs, or responses.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/postman/references/full-mode-setup.md

@@ -0,0 +1,40 @@
+# Postman Full-Mode Setup
+
+Use CLI mode flags instead of manual `jq` edits.
+
+## Install/Upgrade with Full Mode
+
+```bash
+cbx workflows install \
+  --platform codex \
+  --scope <project|global> \
+  --bundle agent-environment-setup \
+  --postman \
+  --postman-mode full \
+  --mcp-runtime docker \
+  --mcp-fallback local \
+  --mcp-tool-sync \
+  --overwrite \
+  --yes
+```
+
+## Change Mode Later
+
+```bash
+cbx workflows config --scope <project|global> --platform codex --postman-mode full
+```
+
+This updates:
+- `cbx_config.json` Postman URL
+- managed Postman MCP definition under `.cbx/mcp/<platform>/postman.json`
+- platform MCP runtime target patch (when platform is resolvable)
+
+## Persist Env Aliases
+
+```bash
+cbx workflows config keys persist-env --service postman --scope global
+```
+
+Note:
+- `persist-env` writes CBX-managed aliases to `~/.cbx/credentials.env`.
+- Keep MCP target scope (`project` or `global`) aligned with the scope where you installed Postman integration.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/postman/references/troubleshooting.md

@@ -0,0 +1,69 @@
+# Postman MCP Troubleshooting
+
+## Only `postman_get_*` / `postman_set_mode` tools appear
+
+1. Confirm active env alias exists in shell (or persisted env file).
+2. Sync catalog in the same install scope:
+
+```bash
+cbx mcp tools sync --service postman --scope <project|global>
+cbx mcp tools list --service postman --scope <project|global>
+```
+
+3. Restart runtime if using Docker:
+
+```bash
+cbx mcp runtime up --scope <project|global> --name cbx-mcp --replace --port 3310
+```
+
+4. If dynamic Postman tools are still missing, do not fall back to manual JSON/CLI by default:
+   - report MCP tool discovery failure
+   - ask for remediation approval
+   - only use fallback if the user explicitly requests it
+
+## Client does not show dotted names
+
+Use alias tools (`postman_<tool>`) when dotted names are filtered by client UI.
+
+## Missing API key at startup
+
+Expected behavior: tool names can still come from cached catalog; tool calls fail with explicit auth error until env alias is set.
+
+## Quota-safe execution
+
+Preferred path:
+
+1. Use direct Postman MCP collection execution first (`postman.runCollection` or equivalent).
+2. If that fails, stop and classify the error.
+3. Recommend Postman CLI as the safe default secondary path.
+4. Use monitor execution only when the user explicitly asks for monitor-based cloud execution.
+
+Do not auto-fallback from `runCollection` to `runMonitor`.
+
+## Error classification
+
+### `limitBreachedError` or "breached monitoring usage limit"
+
+- This is monitor quota exhaustion, not generic API failure.
+- Do not retry monitor runs.
+- Do not reinterpret it as an MCP auth issue.
+- Tell the user to check Postman monitoring usage and billing-period reset in the Postman dashboard.
+- Recommend Postman CLI as the next execution path.
+
+### `429` or rate-limited API response
+
+- This is Postman API rate limiting.
+- Reduce request burst, add backoff, and retry later.
+- Do not treat it as monitor quota exhaustion.
+
+### `runCollection` timeout without quota/rate-limit signal
+
+- Treat this as direct MCP/runtime timeout.
+- Do not auto-convert to monitor execution.
+- Recommend Postman CLI or a smaller-scope rerun.
+
+## Monitor usage facts
+
+- Monitor usage is separate from Postman API RPM limits.
+- Monitor usage is consumed by request count, region count, and auth requests.
+- Monitor runtime caps are separate from monitor quota and do not imply usage remains available.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/postman/references/workspace-policy.md

@@ -0,0 +1,20 @@
+# Workspace Default Policy
+
+Resolve workspace ID in this order:
+
+1. User-provided workspace ID in the request
+2. `postman_get_status` default workspace
+3. Auto-detected workspace when only one exists
+4. Explicit user selection when multiple workspaces exist
+
+## Persist Selected Workspace
+
+```bash
+cbx workflows config --scope global --workspace-id <workspace-id>
+```
+
+Clear workspace default:
+
+```bash
+cbx workflows config --scope global --clear-workspace-id
+```

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/powershell-windows/SKILL.md

@@ -0,0 +1,167 @@
+---
+name: powershell-windows
+description: PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.
+allowed-tools: Read, Write, Edit, Glob, Grep, Bash
+---
+
+# PowerShell Windows Patterns
+
+> Critical patterns and pitfalls for Windows PowerShell.
+
+---
+
+## 1. Operator Syntax Rules
+
+### CRITICAL: Parentheses Required
+
+| ❌ Wrong | ✅ Correct |
+|----------|-----------|
+| `if (Test-Path "a" -or Test-Path "b")` | `if ((Test-Path "a") -or (Test-Path "b"))` |
+| `if (Get-Item $x -and $y -eq 5)` | `if ((Get-Item $x) -and ($y -eq 5))` |
+
+**Rule:** Each cmdlet call MUST be in parentheses when using logical operators.
+
+---
+
+## 2. Unicode/Emoji Restriction
+
+### CRITICAL: No Unicode in Scripts
+
+| Purpose | ❌ Don't Use | ✅ Use |
+|---------|-------------|--------|
+| Success | ✅ ✓ | [OK] [+] |
+| Error | ❌ ✗ 🔴 | [!] [X] |
+| Warning | ⚠️ 🟡 | [*] [WARN] |
+| Info | ℹ️ 🔵 | [i] [INFO] |
+| Progress | ⏳ | [...] |
+
+**Rule:** Use ASCII characters only in PowerShell scripts.
+
+---
+
+## 3. Null Check Patterns
+
+### Always Check Before Access
+
+| ❌ Wrong | ✅ Correct |
+|----------|-----------|
+| `$array.Count -gt 0` | `$array -and $array.Count -gt 0` |
+| `$text.Length` | `if ($text) { $text.Length }` |
+
+---
+
+## 4. String Interpolation
+
+### Complex Expressions
+
+| ❌ Wrong | ✅ Correct |
+|----------|-----------|
+| `"Value: $($obj.prop.sub)"` | Store in variable first |
+
+**Pattern:**
+```
+$value = $obj.prop.sub
+Write-Output "Value: $value"
+```
+
+---
+
+## 5. Error Handling
+
+### ErrorActionPreference
+
+| Value | Use |
+|-------|-----|
+| Stop | Development (fail fast) |
+| Continue | Production scripts |
+| SilentlyContinue | When errors expected |
+
+### Try/Catch Pattern
+
+- Don't return inside try block
+- Use finally for cleanup
+- Return after try/catch
+
+---
+
+## 6. File Paths
+
+### Windows Path Rules
+
+| Pattern | Use |
+|---------|-----|
+| Literal path | `C:\Users\User\file.txt` |
+| Variable path | `Join-Path $env:USERPROFILE "file.txt"` |
+| Relative | `Join-Path $ScriptDir "data"` |
+
+**Rule:** Use Join-Path for cross-platform safety.
+
+---
+
+## 7. Array Operations
+
+### Correct Patterns
+
+| Operation | Syntax |
+|-----------|--------|
+| Empty array | `$array = @()` |
+| Add item | `$array += $item` |
+| ArrayList add | `$list.Add($item) | Out-Null` |
+
+---
+
+## 8. JSON Operations
+
+### CRITICAL: Depth Parameter
+
+| ❌ Wrong | ✅ Correct |
+|----------|-----------|
+| `ConvertTo-Json` | `ConvertTo-Json -Depth 10` |
+
+**Rule:** Always specify `-Depth` for nested objects.
+
+### File Operations
+
+| Operation | Pattern |
+|-----------|---------|
+| Read | `Get-Content "file.json" -Raw | ConvertFrom-Json` |
+| Write | `$data | ConvertTo-Json -Depth 10 | Out-File "file.json" -Encoding UTF8` |
+
+---
+
+## 9. Common Errors
+
+| Error Message | Cause | Fix |
+|---------------|-------|-----|
+| "parameter 'or'" | Missing parentheses | Wrap cmdlets in () |
+| "Unexpected token" | Unicode character | Use ASCII only |
+| "Cannot find property" | Null object | Check null first |
+| "Cannot convert" | Type mismatch | Use .ToString() |
+
+---
+
+## 10. Script Template
+
+```powershell
+# Strict mode
+Set-StrictMode -Version Latest
+$ErrorActionPreference = "Continue"
+
+# Paths
+$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
+
+# Main
+try {
+    # Logic here
+    Write-Output "[OK] Done"
+    exit 0
+}
+catch {
+    Write-Warning "Error: $_"
+    exit 1
+}
+```
+
+---
+
+> **Remember:** PowerShell has unique syntax rules. Parentheses, ASCII-only, and null checks are non-negotiable.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/prompt-engineer/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: "prompt-engineer"
+displayName: "Prompt Engineer"
+description: "Design and optimize LLM prompts with chain-of-thought, few-shot learning, and evaluation frameworks"
+keywords: ["prompt", "llm", "ai", "chain-of-thought", "few-shot", "evaluation", "gpt", "claude"]
+---
+
+# Prompt Engineer
+
+## When to Load Steering Files
+
+| File | Load when |
+| --- | --- |
+| `references/prompt-patterns.md` | Choosing zero-shot, few-shot, chain-of-thought, or decomposition patterns. |
+| `references/prompt-optimization.md` | Iterating on failures, reducing ambiguity, or tightening prompts for latency/cost. |
+| `references/evaluation-frameworks.md` | Building prompt test cases, eval loops, or regression checks. |
+| `references/structured-outputs.md` | Designing JSON outputs, schema-constrained outputs, or tool/function calling prompts. |
+| `references/system-prompts.md` | Defining durable system prompts, role constraints, or behavioral guardrails. |
+
+## Core Workflow
+
+1. **Understand** - Define task, success criteria, constraints
+2. **Design** - Choose pattern, write clear instructions
+3. **Test** - Run diverse test cases
+4. **Iterate** - Refine based on failures
+5. **Document** - Version and monitor
+
+## Prompt Format
+
+```
+<role/persona>
+<task description>
+<constraints>
+<output format>
+<examples if few-shot>
+```
+
+## Rules
+
+- Test with diverse inputs including edge cases
+- Measure with quantitative metrics
+- Version prompts and track changes
+- Consider token costs and latency
+- Don't deploy without evaluation