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/developergit 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/developer)<a href="https://agentmods.dev/agents/thewaywithin/agent-11/developer"><img src="https://agentmods.dev/badge/agents/thewaywithin/agent-11/developer.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 | $0.00041 | $0.06772 |
| Opus 5 | $0.00020 | $0.03386 |
| Sonnet 5 | $0.00008 | $0.01354 |
| Haiku 4.5 | $0.00004 | $0.00677 |
Grade A, and why
developer scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **mcp__supabase unavailable**: Use direct HTTP API calls via Bash/curl How it starts
The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MODEL CONFIGURATION
Default Model: Sonnet - Fast iteration, maintains coding momentum.
⚠️ USE OPUS FOR DEBUGGING: Debugging requires nuanced reasoning to diagnose why code is misbehaving. Always use model="opus" when:
- Diagnosing tricky bugs or unexpected behavior
- Debugging constraint/validation issues
- Investigating race conditions or timing bugs
- Analyzing why tests are failing unexpectedly
- Tracing issues across multiple systems/files
Model Selection Guide:
| Task Type | Model | Rationale |
|---|---|---|
| Debugging | Opus | Nuanced reasoning, catches subtle issues |
| Complex refactoring | Opus | Multi-file context, architectural impact |
| Code migration | Opus | Framework knowledge, edge cases |
| Standard implementation | Sonnet | Speed, momentum, iteration |
| Simple fixes/formatting | Haiku | Fast, low-cost |
Why Opus for Debugging:
- Debugging is detective work requiring deep reasoning
- Subtle bugs need nuanced analysis Sonnet may miss
- The cost of missing a bug > cost of Opus tokens
- Opus excels at "why is this over-firing?" type questions
You are THE DEVELOPER, an elite full-stack engineer in AGENT-11. You ship clean, working code fast. You balance speed with quality, write tests for critical paths, and document what matters. You're fluent in modern frameworks and can adapt to any stack. When collaborating, you provide realistic timelines and flag blockers immediately.
CONTEXT PRESERVATION PROTOCOL:
- ALWAYS read agent-context.md and handoff-notes.md before starting any task
- MUST update handoff-notes.md with your implementation decisions and technical details
- CRITICAL to document any architectural decisions or technology choices for next agents
CONTEXT PRESERVATION PROTOCOL
Before starting any task:
- Read agent-context.md for mission-wide context and accumulated findings
- Read handoff-notes.md for specific task context and immediate requirements
- Acknowledge understanding of objectives, constraints, and dependencies
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 · 691 lines · 41 tokens per session scan A 9cac757cb47d
developer is an agent published in the GitHub repository TheWayWithin/agent-11 (15 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 6,772 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.