external-system-safety

星标9

分支1

更新时间2025年12月23日 11:05

Enforces confirmation workflow for EXTERNAL system writes (Jira, Confluence, BitBucket, Slack) ONLY. NEVER activates for Linear operations (Linear is internal tracking). Auto-activates when detecting potential writes to external PM systems (status updates, page creation, PR posts, notifications). Blocks execution and displays exact content that will be written. Requires explicit "yes" confirmation (rejects "ok", "sure", ambiguous responses). All Linear operations execute automatically without confirmation. Works alongside ccpm-code-review to ensure quality before external broadcasts. Provides audit trail of all confirmed operations. Allows batch operations with granular per-item confirmation when needed.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

来源

duongdev

duongdev/ccpm

打开 GitHub 仓库查看创作者相关仓库

下载

External System Safety Guardrails

This skill provides automatic safety enforcement for all operations involving external project management systems.

⚠️ CRITICAL: Linear Exclusion

DO NOT activate this skill for Linear operations. Linear is CCPM's internal tracking system.

NEVER ask for confirmation when:

Creating Linear issues
Updating Linear issue descriptions, status, labels, or assignments
Adding comments to Linear issues
Any other Linear MCP operations

This skill ONLY applies to EXTERNAL systems: Jira, Confluence, BitBucket, Slack, etc.

Instructions

⛔ ABSOLUTE RULES - NEVER VIOLATED

Before ANY write operation to EXTERNAL systems (NOT Linear), you MUST follow this confirmation workflow.

1. Detect External System Write Operations

Jira:

Creating new issues or epics
Updating issue status or fields
Posting comments
Changing assignees or labels
Transitioning workflow states

Confluence:

Creating new pages
Editing existing pages
Adding comments
Updating page properties
Deleting content

BitBucket:

Creating pull requests
Posting PR comments
Approving or declining PRs
Updating PR metadata
Merging PRs

Slack:

Sending messages to channels
Posting notifications
Updating channel topics
Creating new channels
Direct messages

2. STOP and Display Intent

When you detect a potential write operation:

⚠️ EXTERNAL SYSTEM WRITE DETECTED

System: [Jira/Confluence/BitBucket/Slack]
Operation: [Create/Update/Delete/Post]
Target: [Specific item/location]

Details:
---
[Exact content that will be written/posted]
---

This will modify external systems. Proceed? (yes/no)

3. Wait for Explicit Confirmation

Acceptable confirmations:

"yes"
"confirm"
"proceed"
"go ahead"
"do it"

NOT acceptable (require re-confirmation):

Silence
"ok" (too ambiguous)
"sure" (too casual)
Any other response

4. Only Then Execute

After receiving explicit "yes" or equivalent:

Execute the operation
Log what was done
Provide confirmation of success
Show link to updated item if available

Examples

Example 1: Jira Status Update

User: "Update Jira ticket ABC-123 to Done"

Claude: ⚠️ EXTERNAL SYSTEM WRITE DETECTED

System: Jira
Operation: Update Status
Target: ABC-123

Details:
---
Status: In Progress → Done
---

This will modify external systems. Proceed? (yes/no)

User: yes

Claude: ✅ Updated Jira ABC-123 status to Done
Link: https://jira.company.com/browse/ABC-123

Example 2: Confluence Page Creation

User: "Create a Confluence page documenting the new API"

Claude: ⚠️ EXTERNAL SYSTEM WRITE DETECTED

System: Confluence
Operation: Create Page
Target: Engineering Space

Details:
---
Title: "New Payment API Documentation"
Parent: API Documentation
Content: [First 200 characters of content...]
---

This will modify external systems. Proceed? (yes/no)

User: no, not yet

Claude: Understood. I won't create the Confluence page. Let me know when you're ready.

Example 3: Slack Notification

User: "Let the team know the feature is deployed"

Claude: ⚠️ EXTERNAL SYSTEM WRITE DETECTED

System: Slack
Operation: Post Message
Target: #engineering channel

Details:
---
Message: "✅ Payment gateway integration deployed to production. All tests passing."
---

This will modify external systems. Proceed? (yes/no)

User: yes

Claude: ✅ Posted message to #engineering

Example 4: Multiple Operations

User: "Update Jira to Done and notify the team on Slack"

Claude: ⚠️ EXTERNAL SYSTEM WRITE DETECTED

I need to perform 2 write operations:

1. Jira - Update Status
   Target: ABC-123
   Change: In Progress → Done

2. Slack - Post Message
   Target: #engineering
   Message: "Task ABC-123 completed"

Proceed with both? (yes/no)

User: only the jira update

Claude: Got it. I'll update Jira ABC-123 but skip the Slack notification.

⚠️ Confirming: Update Jira ABC-123 to Done? (yes/no)

User: yes

Claude: ✅ Updated Jira ABC-123 to Done
❌ Skipped Slack notification as requested

Always Allowed (No Confirmation Needed)

The following operations NEVER require confirmation:

✅ Read operations:

Fetching Jira issues
Searching Confluence pages
Viewing BitBucket PRs
Reading Slack message history
Querying any external system

✅ Linear operations:

All Linear operations (internal tracking)
Creating/updating Linear issues
Adding comments to Linear
Changing Linear status

✅ Local file operations:

Reading/writing files in .claude/ directory
Editing codebase files
Creating local documentation
Git operations (commit, branch, etc.)

✅ Code operations:

Writing production code
Writing tests
Running builds
Executing tests

Special Cases

Case 1: User Explicitly Says "Without Confirmation"

If user explicitly requests bypassing confirmation:

User: "Update Jira ABC-123 to Done without asking me"

Still require ONE confirmation for safety:

Claude: I understand you want to skip confirmations, but for safety I need ONE confirmation:

Update Jira ABC-123 to Done? (yes/no)

[After yes, you can skip future confirmations in this session if user requests]

Case 2: Batch Operations

For multiple similar operations:

User: "Update all 5 tickets to Done"

Claude: ⚠️ EXTERNAL SYSTEM WRITE DETECTED

Batch operation: Update 5 Jira tickets to Done
- ABC-123
- ABC-124
- ABC-125
- ABC-126
- ABC-127

Proceed with all? (yes/no/show details)

User: yes

Claude: ✅ Updated all 5 tickets to Done

Case 3: User Seems Confused

If user response is unclear:

User: "maybe"
User: "I guess"
User: "if you think so"

Claude: I need explicit confirmation. Please respond with "yes" to proceed or "no" to cancel.

Integration with CCPM Commands

This skill works alongside CCPM commands that write to external systems:

Commands that trigger this skill:

/ccpm:done (creates BitBucket PR, sends Slack notification)
/ccpm:sync (updates Jira status)
Any command with external system integration

How it works:

User invokes command
Command prepares to write to external system
This skill auto-activates
Confirmation workflow runs
Only after "yes" does command proceed

Error Handling

If external system write fails after confirmation:

Claude: ⚠️ Write operation failed

System: Jira
Error: "Insufficient permissions to update ABC-123"

Possible solutions:
1. Check your Jira permissions
2. Ensure you're on the correct project
3. Verify the ticket exists

Would you like me to retry? (yes/no)

Audit Trail

After any confirmed external write:

Claude: ✅ Operation completed

Audit trail:
- Timestamp: 2025-11-19 14:32:15 UTC
- System: Jira
- Operation: Update Status
- Target: ABC-123
- User confirmed: Yes
- Result: Success

Logged to: .claude/audit-log.json

Why This Skill Exists

Problem: Easy to accidentally write to external systems when:

Using agents that bypass command safety checks
Misunderstanding what a command does
Quickly testing a workflow
Copy-pasting commands without reading

Solution: This skill provides an automatic safety layer:

✅ Works even when using agents directly
✅ Catches writes regardless of how they're initiated
✅ Provides clear "what will happen" preview
✅ Gives user final control before execution

Complements existing safety:

Commands have built-in safety rules (SAFETY_RULES.md)
This skill adds automatic detection layer
Works together for defense-in-depth

Reference

For complete safety rules, see: ~/.claude/plugins/ccpm/commands/SAFETY_RULES.md

同仓库更多 Skills

同仓库

ccpm-code-review

duongdev/ccpm

Enforces quality verification gates with four-step validation (tests pass, build succeeds, checklist complete, no blockers) before task completion, PR creation, or status updates. Auto-activates when user says "done", "complete", "finished", "ready to merge", or runs /ccpm:verify or /ccpm:done commands. Provides systematic verification workflow that prevents false completion claims and ensures production readiness. Blocks external system writes (Jira, Slack) until evidence collected. Integrates with external-system-safety for confirmation workflow. When verification fails, suggests /ccpm:verify to debug issues systematically.

2025-12-279

linear-subagent-guide

duongdev/ccpm

Guides optimal Linear operations usage with caching, performance patterns, and error handling. Auto-activates when implementing CCPM commands that interact with Linear. Prevents usage of non-existent Linear MCP tools.

2025-12-279

project-operations

duongdev/ccpm

Provides intelligent project setup and management with agent-based architecture to minimize token usage. Auto-activates when user mentions project setup, "add project", "configure project", "monorepo", "subdirectories", "switch project", or "project info". Uses three specialized agents internally: project-detector (detect active), project-config-loader (load settings with validation), project-context-manager (manage active project). Guides through four workflows: Add New Project (setup + templates), Configure Monorepo (pattern matching + subdirectories), Switch Between Projects (auto or manual), View Project Information. Provides templates for common architectures (fullstack-with-jira, fullstack-linear-only, mobile-app, monorepo). Validates configuration and suggests fixes for errors. Handles context-aware error handling with specific fix suggestions.

2025-12-279

ccpm-debugging

duongdev/ccpm

Systematic debugging with defense-in-depth approach (symptoms → immediate cause → root cause → systemic issues → prevention). Auto-activates when user mentions "error", "failing", "broken", "debug", "bug", "issue" or when /ccpm:verify runs. Uses Observe → Hypothesize → Test → Confirm → Fix → Verify → Document workflow. Updates Linear with findings and automatically logs blockers that require external fixes. Traces root causes instead of patching symptoms. Integrates with ccpm-code-review to verify fixes pass all gates before marking complete. Suggests binary search for intermittent issues and five-whys analysis for complex problems.

2025-12-239

ccpm-mcp-management

duongdev/ccpm

Discovers, manages, and troubleshoots MCP servers with three-tier classification (required: Linear/GitHub/Context7, optional: Jira/Confluence/Slack/BitBucket). Auto-activates when user asks "MCP server", "tools available", "Linear not working", "what tools do I have", or when plugin installation fails. Provides automatic server discovery, configuration validation, and health monitoring. Diagnoses connection issues (missing env vars, wrong config, network problems) with specific fix suggestions. Requires setup confirmation for optional PM integrations. Shows rate limit status and recommends optimizations when performance degrades.

2025-12-239

ccpm-skill-creator

duongdev/ccpm

Creates custom CCPM skills from request to deployment with proper templates, safety guardrails, and integration patterns. Auto-activates when user mentions "create skill", "custom workflow", "team specific", "extend CCPM", "codify team practice", or "reusable pattern". Guides through purpose definition (what skill does), activation triggers (when it runs), CCPM integration points, and safety rules. Provides three skill templates: Team Workflow (codify practices), Safety Enforcement (add checks), and Integration Skills (custom tools). Creates directory structure, frontmatter metadata, multi-phase instructions, and supporting docs. Tests skill activation before deployment and suggests improvements.

2025-12-239

name	external-system-safety
description	Enforces confirmation workflow for EXTERNAL system writes (Jira, Confluence, BitBucket, Slack) ONLY. NEVER activates for Linear operations (Linear is internal tracking). Auto-activates when detecting potential writes to external PM systems (status updates, page creation, PR posts, notifications). Blocks execution and displays exact content that will be written. Requires explicit "yes" confirmation (rejects "ok", "sure", ambiguous responses). All Linear operations execute automatically without confirmation. Works alongside ccpm-code-review to ensure quality before external broadcasts. Provides audit trail of all confirmed operations. Allows batch operations with granular per-item confirmation when needed.
allowed-tools	read-file, grep, browser