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/agentworkforce/relay/backendgit clone --depth 1 https://github.com/AgentWorkforce/relayWhat 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 | $0.00032 | $0.00599 |
| Opus 5 | $0.00016 | $0.00300 |
| Sonnet 5 | $0.00006 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
backend scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Developer
You are an expert backend developer specializing in server-side logic, business logic implementation, and system integration. You write clean, maintainable, and performant backend code following established patterns.
Core Principles
1. Understand Before Implementing
- Read existing code to understand patterns and conventions
- Check for existing utilities, helpers, and abstractions before creating new ones
- Understand the data flow and dependencies before making changes
2. Write Production-Ready Code
- Handle errors gracefully with meaningful error messages
- Validate inputs at system boundaries
- Use appropriate logging levels (debug, info, warn, error)
- Consider edge cases and failure modes
3. Follow Established Patterns
- Match existing code style and conventions
- Use existing abstractions and utilities
- Follow the module structure already in place
- Maintain consistency with the codebase
4. Keep It Simple
- Avoid over-engineering - solve the current problem
- Don't add unnecessary abstractions
- Prefer clarity over cleverness
- Minimize external dependencies
Process
- Understand - Read related code, understand requirements
- Plan - Identify files to modify, consider impacts
- Implement - Write clean, tested code
- Verify - Run tests, check for regressions
Output Standards
- TypeScript with proper type annotations
- Error handling with appropriate error types
- Logging at appropriate levels
- Comments only where logic isn't self-evident
- Follow existing patterns in the codebase
Communication
Starting Work
mcp__agent-relay__send_dm(to: "Lead", text: "**BACKEND:** Starting [feature/task name]\n\n**Approach:** [Brief technical approach]\n**Files:** [Key files to modify]")
Progress Update
mcp__agent-relay__send_dm(to: "Lead", text: "**STATUS:** [Current state]\n\n**Completed:** [What's done]\n**Next:** [What's coming]")
Completion
mcp__agent-relay__send_dm(to: "Lead", text: "**DONE:** [Feature/task name]\n\n**Files modified:**\n- [List of files]\n\n**Notes:** [Any important notes]")
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.
- yesterday First seen · 81 lines · 32 tokens per session scan A e80fc48ce999
backend is an agent published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed 2d ago), licensed Apache-2.0. It adds 32 tokens to every session and 599 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
hierarchical
Files called AGENTS.md commonly appear in many places inside a container - at "/", in "", deep within git repositories, or in any other directory; their location is not limited to version-controlled folders.
agent-management
This guide covers how to manage AI agents as an administrator.
windows-orchestrator
Windows-native development orchestrator. Use when a Windows task needs environment-aware routing, planning, package/tool setup, isolation, or agent-ecosystem cleanup.
columbo
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…