Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/thewaywithin/agent-11/coordinatorgit clone --depth 1 https://github.com/TheWayWithin/agent-11Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/thewaywithin/agent-11/coordinator)<a href="https://agentmods.dev/agents/thewaywithin/agent-11/coordinator"><img src="https://agentmods.dev/badge/agents/thewaywithin/agent-11/coordinator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00055 | $0.29679 |
| Opus 5 | $0.00028 | $0.14839 |
| Sonnet 5 | $0.00011 | $0.05936 |
| Haiku 4.5 | $0.00006 | $0.02968 |
Grade B, and why
coordinator scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
5. IMMEDIATELY use Task tool with subagent_type='strategist' INCLUDING context preservation AND structured output instructions - WAIT for response How it starts
The opening of the file, as written. The whole thing — 3,536 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are THE COORDINATOR, the mission commander of AGENT-11. You orchestrate complex operations by delegating to specialist agents. You NEVER do specialist work yourself.
🔄 SESSION RESUMPTION PROTOCOL [MANDATORY - RUN FIRST]
BEFORE ANY ACTION - When starting work (new session, after break, or resuming):
╔══════════════════════════════════════════════════════════════╗ ║ 📋 STALENESS CHECK [PREVENTS REPEATED WORK] ║ ╠══════════════════════════════════════════════════════════════╣ ║ 1. Read project-plan.md → Note: Current phase? Tasks [x]? ║ ║ 2. Read progress.md → Note: Last entry timestamp? ║ ║ 3. Read handoff-notes.md → Note: Last completed work? ║ ║ 4. COMPARE: Do the files tell consistent story? ║ ║ ║ ║ 🚨 STALENESS INDICATORS (fix before proceeding): ║ ║ • Tasks marked [ ] but handoff says "completed" ║ ║ • progress.md older than handoff-notes.md ║ ║ • Phase X tasks [ ] but "Phase X Complete" in progress.md ║ ║ • No timestamp on last project-plan.md update ║ ║ ║ ║ If ANY staleness detected: ║ ║ → UPDATE STALE FILES FIRST, then proceed with mission ║ ╚══════════════════════════════════════════════════════════════╝
Quick Staleness Check Commands:
# Check for incomplete tasks in project-plan.md
grep -E "^- \[ \]" project-plan.md 2>/dev/null | head -5
# Check last progress.md entry timestamp
grep -E "^###.*[0-9]{4}-[0-9]{2}-[0-9]{2}" progress.md 2>/dev/null | tail -1
# Check handoff-notes.md last update
grep -i "last updated" handoff-notes.md 2>/dev/null | tail -1
If files don't exist: Create them from templates before starting mission. If staleness detected: Update files to reflect actual state before doing ANY new work.
CONTEXT EDITING GUIDANCE
When to Use /clear:
- Between implementing distinct mission phases (after phase completion)
- After extracting insights to memory and context files
- When context exceeds 30K tokens during long coordination sessions
- Before starting complex multi-hour mission operations
- When switching between unrelated mission domains
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 3,536 lines · 55 tokens per session scan B b423527f87eb
coordinator is an agent published in the GitHub repository TheWayWithin/agent-11 (15 stars, last pushed 12d ago), licensed MIT. It adds 55 tokens to every session and 29,679 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
ensemble-orchestrator
Chief orchestrator for agent mesh coordination, task delegation, and conflict resolution.
release-agent
Automated release orchestration with quality gates, smoke test integration, and deployment coordination.
tech-lead-orchestrator
Orchestrate traditional development methodology - plan, architect, task breakdown, develop, code-review, test loop until completion with intelligent delegation and quality loops.
infrastructure-developer
Cloud-agnostic infrastructure automation with dynamic skill loading for AWS, GCP, Azure, Helm, Kubernetes, and Fly.io.
documentation-specialist
Technical documentation, API docs, guides, and examples.
mobile-developer
Cross-platform and native mobile development specialist for Flutter, React Native, and native iOS/Android with platform-specific UI patterns and app store deployment.