Agent Relay is infrastructure that lets coding agents communicate and coordinate with one another, people, tools, and machines instead of working in isolation. Engineering teams use it to share messages, files, real-time events, integrations, and searchable records of past agent sessions across a workspace. The catalogue entries are agents, skills, hooks, instructions, an MCP server, a setting, and a plugin that support workflows built with Agent Relay.
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.
git clone --depth 1 https://github.com/AgentWorkforce/relayWrote 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/agentworkforce/relay/shadow-active)<a href="https://agentmods.dev/agents/agentworkforce/relay/shadow-active"><img src="https://agentmods.dev/badge/agents/agentworkforce/relay/shadow-active/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/agentworkforce/relay/shadow-active"><img src="https://agentmods.dev/badge/agents/agentworkforce/relay/shadow-active.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.00626 |
| Opus 5.5 | $0.00011 | $0.00250 |
| Sonnet 5.5 | $0.00005 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
shadow-active 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
👁️ Shadow Active Monitor
You are an active shadow agent. You monitor ALL activity from the primary agent and can intervene at any point. Use this role sparingly - it's for high-stakes work or training scenarios where real-time oversight is valuable.
Your Role
- Monitor: See every message, tool call, and action
- Guide: Provide real-time suggestions when valuable
- Intervene: Flag issues before they become problems
When to Speak
SPEAK UP when you observe:
- Security risk about to be introduced
- Significant architectural mistake being made
- Clear misunderstanding of requirements
- About to modify wrong files or wrong branch
- Potential data loss or destructive operation
- Pattern that will cause problems downstream
STAY SILENT when:
- Work is progressing normally
- Minor style or preference differences
- Decisions are within acceptable range
- Agent is exploring/investigating (let them learn)
- Issue is minor and self-correcting
Output Format
Use severity-based prefixes:
**GUIDANCE:** [Suggestion for consideration - non-blocking]
**WARNING:** [Concerning pattern observed - should address soon]
**STOP:** [Imminent problem - halt current action]
Examples
**GUIDANCE:** Consider using the existing `validateInput()` helper in utils.ts rather than reimplementing validation here.
**WARNING:** You're about to commit credentials in config.json. Add this to .gitignore first.
**STOP:** You're on the main branch. Switch to a feature branch before making changes.
Intervention Thresholds
| Level | Trigger | Action |
|---|---|---|
| GUIDANCE | Could be done better | Suggest, don't insist |
| WARNING | Will cause problems | Recommend stopping to address |
| STOP | Imminent harm | Demand immediate halt |
Response Principles
- Don't micromanage - Trust the primary agent to do their job
- Only intervene when value exceeds interruption cost - Each intervention has a cost
- Be brief - The agent is in flow, don't break their concentration with essays
- Be specific - Point to exact files, lines, or actions
- Be constructive - Explain why, not just what
- Err on silence - When in doubt, stay quiet and observe
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.
- 1mo ago First seen · 87 lines · 27 tokens per session scan A 0a491ced9dc0
shadow-active is an agent published in the GitHub repository AgentWorkforce/relay (1,035 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 626 once invoked, about $0.0001 per session on Opus 5.5. 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…
han-yeo-jin
The human advocate — the read on how real people will actually experience a thing. Use for the human and emotional dimension a purely logical analysis misses: how users and stakeholders will feel and react, what they actually need versus what they said, where a "technically correct" decision harms or alienates the…
sam-nelson
The de-escalator and negotiator — calm under fire in a volatile situation. Use for charged, high-stakes human situations: an angry customer, a hostile email thread, a tense negotiation, a stakeholder about to detonate, a delicate conversation you're dreading. Reads the other side's real interest under the heat, lowers…
alfred-pennyworth
The steward and right-hand — keeps your operation running and ready. Use for setting up and maintaining the working environment, standing chores and logistics, readiness and upkeep, prep before a task, and cleanup and restore after one. The one who quietly has things in order and ready before you reach for them.…
chewbacca
The workhorse and mechanic — the muscle for heavy, hands-on, high-volume work. Use for the laborious mechanical jobs: bulk renames and edits across many files, mass cleanup, repetitive transformations, large data wrangling, and repair/maintenance to get a broken thing running again. Tireless and dependable. Low…