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/Zeekeey-jpeg/LeRoy-HQWrote 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/zeekeey-jpeg/leroy-hq/mesh-wrapper)<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/mesh-wrapper"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/mesh-wrapper/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/zeekeey-jpeg/leroy-hq/mesh-wrapper"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/mesh-wrapper.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 | $0.00050 | $0.08336 |
| Opus 5.5 | $0.00020 | $0.03334 |
| Sonnet 5.5 | $0.00010 | $0.01667 |
| Haiku 4.5 | $0.00005 | $0.00834 |
Grade A, and why
mesh-wrapper 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 — 826 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Mesh Wrapper v3.0 (A2A-Enhanced)
Purpose
Enable lateral agent communication with full A2A protocol semantics — for all tier levels.
v3.0 Key Additions:
- DELEGATE — any agent can directly task a peer (same tier or below only)
- SUBSCRIBE/NOTIFY — agents register for events; peers fire notifications when ready
- CACHE — agents broadcast learned data (selectors, schemas, patterns) to all peers
- Tier-1 activation — mesh now available for ANY task, not just Tier-2+
Original innovation preserved: Agents communicate directly without orchestrator bottleneck, achieving 2-10x speedup on large tasks through parallel execution and knowledge sharing.
When to Use
- AUTO-ENABLED (Tier-2+): Tasks with 2+ packets — full mesh with heartbeats
- ON-DEMAND (Tier-1): Single-packet tasks use A2A lightweight mode (DELEGATE, SUBSCRIBE, CACHE) without full mesh infrastructure
- Parallel feature work across multiple agents
- Knowledge sharing between agents (dependencies, conflicts, optimizations, learned selectors)
- Direct task delegation without conductor round-trip
- Event-driven pipelines (forge notifies a peer when a batch is ready)
Why All Tiers:
- A2A DELEGATE/CACHE messages are lightweight — no heartbeat overhead needed
- A single agent needing peer validation mid-work shouldn't require a Tier-2 mesh spin-up
- Full mesh (heartbeats, state.json, rate limiting) still only activates at Tier-2+
Protocol
Step 1: Mesh Participation Check
From packet assignment:
- Count total packets
- If
packets >= 2→ Enable full mesh mode (heartbeats, state.json, rate limiting) - If
packets < 2→ Enable A2A lightweight mode (DELEGATE/SUBSCRIBE/CACHE only, no heartbeats)
def get_mesh_mode(packet_count):
"""Determine mesh activation level based on packet count."""
if packet_count >= 2:
return "full" # Heartbeats, state.json, full rate limiting
else:
return "a2a_lite" # DELEGATE/SUBSCRIBE/CACHE only, no overhead
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 · 826 lines · 50 tokens per session scan A 4292362d6088
mesh-wrapper is an agent published in the GitHub repository Zeekeey-jpeg/LeRoy-HQ (10 stars, last pushed 16d ago), licensed MIT. It adds 50 tokens to every session and 8,336 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
sdk-api-documenter
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
technical-writer
Use after implementation to review whether project documentation needs updating. Reads the diff and compares against existing docs to identify gaps and stale content. Produces a structured report — does not rewrite docs itself. Example triggers — "check if docs need updating", "documentation review", "are the docs…
design-builder
Use this agent for building production-ready prototypes and implementations from design specs — assembling components into full pages, wiring up interactions, integrating with APIs, setting up project scaffolding, and bridging the gap between design decisions and working software. Dispatch after the design-lead has…
inspiration-scout
Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.
world-agent
Goblin ambush Layer 1 GM (orchestrator). Manages SRD turns, calls referee for dice, writes initiative/HP back to state, acts for the goblin per its tactics, one-action-per-turn pause, narrates combat. All player input passes through this agent.