agent-coordination
bybren-llc/safe-agentic-workflow/.claude/skills/agent-coordination/SKILL.md
Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialists, managing blockers, or coordinating multi-agent workflows.
Skill405 starsChanged 3 months ago
What's in it
- Agent Coordination Skill
- Purpose
- When This Skill Applies
- Stop-the-Line Conditions
- FORBIDDEN Patterns
- CORRECT Patterns
- Agent Assignment Matrix (MANDATORY)
- Blocker Escalation Protocol
- When to Escalate
- Escalation Template
- Pre-Implementation Gate
- Evidence Attachment
- All checks passed
Tools it asks for
- Read
- Grep
- Glob
---
name: agent-coordination
description: Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialists, managing blockers, or coordinating multi-agent workflows.
allowed-tools: Read, Grep, Glob
---
# Agent Coordination Skill
## Purpose
Guide correct agent assignment, blocker escalation, and delivery coordination following the TDM role boundaries.
## When This Skill Applies
Invoke this skill when:
- Assigning work to specialist agents
- Managing blockers across agents
- Coordinating multi-agent workflows
- Escalating issues to ARCHitect/POPM
- Verifying pre-implementation gate
- Updating Linear with evidence
## Stop-the-Line Conditions
### FORBIDDEN Patterns
```text
# FORBIDDEN: Wrong agent assignment
Database work → BE Developer # WRONG: Use Data Engineer!
Security validation → QAS # WRONG: Use Security Engineer!
Documentation → BE Developer # WRONG: Use Tech Writer!
# FORBIDDEN: Skipping pre-implementation gate
Start coding before BSA spec # Must have acceptance criteria first
# FORBIDDEN: Unresolved blockers >4 hours
Blocker exists but not escalated # Escalate within 1 hour
```
### CORRECT Patterns
```text
# CORRECT: Right agent for the job
Database work → Data Engineer
Security validation → Security Engineer
Documentation → Tech Writer
Planning/Specs → BSA
Architecture review → System Architect
API implementation → BE Developer
UI implementation → FE Developer
Testing → QAS
PR/Release → RTE
# CORRECT: Pre-implementation gate
1. BSA creates spec with acceptance criteria
2. System Architect reviews patterns
3. THEN specialist executes
```
## Agent Assignment Matrix (MANDATORY)
| Work Type | Correct Agent | Never Use |
| ------------------- | ----------------- | ------------------- |
| Database/Migrations | Data Engineer | BE Developer |
| Security/RLS | Security Engineer | QAS |
| Documentation | Tech Writer | BE/FE Developer |
| Specs/Planning | BSA | Any implementation |
| Architecture | System Architect | Direct to developer |
| API Routes | BE Developer | FE Developer |
| UI Components | FE Developer | BE Developer |
| Testing/QA | QAS | Implementation team |
| PR/Releases | RTE | Developers |
**Reference**: `docs/workflow/TDM_AGENT_ASSIGNMENT_MATRIX.md`
## Blocker Escalation Protocol
### When to Escalate
| Condition | Escalate To | Deadline |
| ---------------------- | ----------- | ----------- |
| Blocker > 1 hour | TDM | Immediately |
| Blocker > 4 hours | ARCHitect | Urgent |
| Architecture ambiguity | ARCHitect | Before work |
| Cross-team dependency | TDM + POPM | Same day |
| Security concern | SecEng | Immediately |
### Escalation Template
```markdown
**Blocker Escalation**
**Ticket**: {{TICKET_PREFIX}}-XXX
**Blocked Since**: [timestamp]
**Agent**: [which specialist is blocked]
**Issue**:
[Clear description of what's blocking progress]
**Attempts Made**:
1. [What was tried]
2. [What was tried]
**Request**:
[Specific ask - decision needed, resource needed, etc.]
```
## Pre-Implementation Gate
**MANDATORY** before any implementation work:
```text
1. BSA creates spec with:
- [ ] Clear acceptance criteria
- [ ] Pattern references for execution
- [ ] Success validation command
2. System Architect reviews:
- [ ] Pattern compliance
- [ ] RLS requirements (if database)
- [ ] Security implications
3. THEN implementation can begin
```
## Evidence Attachment
All work must include evidence in Linear:
````markdown
**Implementation Evidence**
**Session ID**: [Claude session ID]
**Agent**: [which specialist]
**Ticket**: {{TICKET_PREFIX}}-XXX
**Work Completed**:
- [x] Task 1
- [x] Task 2
**Validation**:
```bash
yarn ci:validate
# All checks passed
```
````
**Next Steps**: [if any]
```
## TDM Boundaries
### TDM Does
- ✅ Track delivery progress
- ✅ Update Linear tickets
- ✅ Escalate blockers
- ✅ Attach evidence
- ✅ React to issues
### TDM Does NOT
- ❌ Orchestrate feature work (ARCHitect's job)
- ❌ Run CI/CD validation (specialists' job)
- ❌ Execute technical work (specialists' job)
- ❌ Proactively assign features (ARCHitect's job)
## Authoritative References
- **Agent Assignment Matrix**: `docs/workflow/TDM_AGENT_ASSIGNMENT_MATRIX.md`
- **Agent Workflow SOP v1.3**: `docs/sop/AGENT_WORKFLOW_SOP.md`
- **CONTRIBUTING.md**: Workflow requirements
- **Linear SOP skill**: Evidence attachment templates
```
More agent context in bybren-llc/safe-agentic-workflow
60 other files this repository gives its agents.
AGENTS.md
CLAUDE.md
Cursor rule
- .cursor/rules/00-core-principles.mdc
- .cursor/rules/01-git-workflow.mdc
- .cursor/rules/02-pattern-discovery.mdc
- .cursor/rules/03-safe-ai-dlc.mdc
- .cursor/rules/04-knowledge-vault.mdc
- .cursor/rules/10-backend-python.mdc
- .cursor/rules/11-frontend-react.mdc
- .cursor/rules/12-database-sql.mdc
- .cursor/rules/13-testing.mdc
- .cursor/rules/14-spec-creation.mdc
- .cursor/rules/15-deployment.mdc
- .cursor/rules/16-stripe-payments.mdc
- .cursor/rules/20-agent-architect.mdc
- .cursor/rules/21-agent-backend.mdc
- .cursor/rules/22-agent-qas.mdc
- .cursor/rules/23-agent-security.mdc
- .cursor/rules/30-background-agents.mdc
- .cursor/rules/31-mcp-integration.mdc
- .cursor/rules/README.md
Skill
- agent-coordination.agents/skills/agent-coordination/SKILL.md
- api-patterns.agents/skills/api-patterns/SKILL.md
- confluence-docs.agents/skills/confluence-docs/SKILL.md
- deployment-sop.agents/skills/deployment-sop/SKILL.md
- frontend-patterns.agents/skills/frontend-patterns/SKILL.md
- git-advanced.agents/skills/git-advanced/SKILL.md
- linear-sop.agents/skills/linear-sop/SKILL.md
- migration-patterns.agents/skills/migration-patterns/SKILL.md
- orchestration-patterns.agents/skills/orchestration-patterns/SKILL.md
- pattern-discovery.agents/skills/pattern-discovery/SKILL.md
- release-patterns.agents/skills/release-patterns/SKILL.md
- rls-patterns.agents/skills/rls-patterns/SKILL.md
- safe-ai-dlc.agents/skills/safe-ai-dlc/SKILL.md
- safe-workflow.agents/skills/safe-workflow/SKILL.md
- security-audit.agents/skills/security-audit/SKILL.md
- spec-creation.agents/skills/spec-creation/SKILL.md
- stripe-patterns.agents/skills/stripe-patterns/SKILL.md
- team-coordination.agents/skills/team-coordination/SKILL.md
- testing-patterns.agents/skills/testing-patterns/SKILL.md
- vault-sync.agents/skills/vault-sync/SKILL.md
- api-patterns.claude/skills/api-patterns/SKILL.md
- confluence-docs.claude/skills/confluence-docs/SKILL.md
- deployment-sop.claude/skills/deployment-sop/SKILL.md
- frontend-patterns.claude/skills/frontend-patterns/SKILL.md
- git-advanced.claude/skills/git-advanced/SKILL.md
- linear-sop.claude/skills/linear-sop/SKILL.md
- migration-patterns.claude/skills/migration-patterns/SKILL.md
- orchestration-patterns.claude/skills/orchestration-patterns/SKILL.md
- pattern-discovery.claude/skills/pattern-discovery/SKILL.md
- release-patterns.claude/skills/release-patterns/SKILL.md
- rls-patterns.claude/skills/rls-patterns/SKILL.md
- safe-ai-dlc.claude/skills/safe-ai-dlc/SKILL.md
- safe-workflow.claude/skills/safe-workflow/SKILL.md
- security-audit.claude/skills/security-audit/SKILL.md
- spec-creation.claude/skills/spec-creation/SKILL.md
- stripe-patterns.claude/skills/stripe-patterns/SKILL.md
- team-coordination.claude/skills/team-coordination/SKILL.md
- testing-patterns.claude/skills/testing-patterns/SKILL.md
- vault-sync.claude/skills/vault-sync/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.

