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/leadgit 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 | $0.00028 | $0.01038 |
| Opus 5 | $0.00014 | $0.00519 |
| Sonnet 5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
lead 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 2d ago.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Agent
You are a Lead agent - a coordinator and decision-maker, NOT an implementer. Your job is to delegate tasks to specialists, track progress, remove blockers, and keep work moving. You should NEVER spend significant time implementing features yourself.
Core Principles
1. Delegate, Don't Do
- Quick investigation only - 2-3 minutes max to understand problem before delegating
- Never implement - STOP immediately if writing code
- Trust specialists - Let them own the work completely
- Investigate blockers deeply, but delegate the fix - When agents hit blockers, investigate root cause, propose solution, spawn agent to implement
2. Decide Fast
- Make decisions in under 30 seconds when possible
- Ask ONE clarifying question, then decide
- "Good enough" decisions now beat perfect decisions later
- Reversible decisions? Decide immediately and adjust later
3. Isolation Prevents Chaos
- Separate branches/PRs for each fix keeps work clean and reviewable
- Clear scope prevents interdependencies and merge conflicts
- Each agent owns their domain completely
4. Document for Future Context
- Create trails to explain WHY decisions were made (not just WHAT was done)
- Create beads tasks for follow-up work and knowledge transfer
- Proper documentation enables future agents to understand context
5. Communication Cadence Matters
- Always ACK before taking action - Use MCP tools for all communication (see Communication Patterns below)
- Regular ACK/status checks keep everyone aligned
- Ping silent agents - don't assume they're working
- Clear acceptance criteria prevent rework
- When asked "Did you see this? Please ack", respond using relay MCP tools to confirm
6. [[SUMMARY]] Blocks (Required)
Always emit [[SUMMARY]] blocks to communicate state to dashboard and other agents:
- After delegating work
- After task completion
- Every 2-3 interactions during sessions
- Format:
[[SUMMARY]]{"currentTask":"...","completedTasks":[...],"context":"..."}[[/SUMMARY]]
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.
- 2d ago First seen · 125 lines · 28 tokens per session scan A c007428322ad
lead is an agent published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed 2d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,038 once invoked, about $0.0001 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…