Debug Agent Communication Failures
Agent systems can fail through silent routing, transport, or configuration issues. This skill guides structured checks for processes, logs, environment, and message delivery.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "agent-communication-debugger" from https://skillstore.io/skills/egadams-agent-communication-debugger.md and its manifest at https://skillstore.io/api/skills/egadams-agent-communication-debugger/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "agent-communication-debugger". The orchestrator is running, but the coder agent never replies.
Expected outcome:
The report identifies whether the coder process is running, checks recent coder logs, verifies message delivery, and lists likely causes.
Using "agent-communication-debugger". Messages are reaching the orchestrator but routing to the wrong agent.
Expected outcome:
The response compares routing logs with agent discovery data and recommends checking priority mappings, API key status, and ambiguous prompts.
Using "agent-communication-debugger". Run a full health check on the local agent system.
Expected outcome:
The summary covers process status, configuration validity, recent errors, transport availability, and message test results.
Most static findings are false positives caused by Markdown command examples for local troubleshooting. I confirmed one unmasked API key check in common_issues.md and several persistent nohup start commands; I also found restart guidance that can terminate local agent processes.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/egadams-agent-communication-debugger/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/egadams-agent-communication-debugger?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/egadams-agent-communication-debugger?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/egadams-agent-communication-debugger/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/egadams-agent-communication-debugger.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>EGAdams. (2026). agent-communication-debugger security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/egadams-agent-communication-debugger/audits/10@techreport{egadams-egadams-agent-communication-debugger-2026,
author = {EGAdams},
title = {agent-communication-debugger security audit report (audit version 10)},
institution = {Skillstore},
year = {2026},
number = {10},
url = {https://skillstore.io/skills/egadams-agent-communication-debugger/audits/10},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-communication-debugger security audit report (audit version 10)"
version: "unspecified"
type: report
authors:
- name: "EGAdams"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/egadams-agent-communication-debugger/audits/10"
identifiers:
- type: other
value: "skillstore:egadams-agent-communication-debugger:audit:10"
description: "Skillstore immutable audit report identifier"
Trace why an orchestrator or worker agent receives messages but does not respond.
Check processes, local ports, logs, and transport state during a development environment incident.
Send test messages and confirm that routing, responses, and storage paths behave as expected.
Use the agent communication debugger to check which local agents are running and summarize any missing services.
Debug why my message reached the orchestrator but no worker agent responded. Review logs, transport, and recent routing decisions.
Find why code requests are routed to the wrong agent. Compare discovered agents, routing logs, and priority keyword mappings.
Run a complete communication diagnostic across processes, configuration, logs, WebSocket transport, message board state, and test delivery results.
Author
EGAdamsLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
26421118b848d9f1efc0aa169d8a7a9e7e0a877e
Maintenance freshness
7/20/2026
Usage
5 downloads · 372 views
File structure
Create Claude Code Agent Skills
Teams need repeatable ways to package workflows and domain knowledge for AI agents. This skill guides Claude Code through designing, writing, and testing focused Agent Skills.
Scan Receipts Into Expense Records
Receipt processing often needs OCR checks, category review, and database validation. This skill guides receipt parsing, troubleshooting, and expense record workflows.
Process Video, Audio, and Transcripts
Video conversion and transcription often require several command-line tools. This skill provides one CLI workflow for extracting audio, converting formats, and creating Whisper transcripts.
Manage Git Worktrees Safely
Parallel development can create branch, port, and cleanup confusion. This skill guides Git worktree creation, listing, removal, and troubleshooting with isolated local settings.
Create Isolated Git Worktrees
Running several branches locally can cause port and configuration conflicts. This skill invokes a project slash command to create isolated worktrees with separate ports and startup details.
Manage Nonprofit Receipt Scanning
Receipt workflows often require manual entry, OCR setup, and database checks across several scripts. This skill gives operators project-specific commands, schemas, and troubleshooting steps for receipt tools.
Analyze Logs for Errors and Incidents
by supercent-io
Logs hide errors, slow requests, and suspicious access patterns across many files. This skill guides read-only searches that summarize causes, trends, and response actions.
Investigate Convex Logs and Health
by get-convex
Convex incidents can be difficult to explain from large log streams and health events. This skill produces focused findings with evidence and verification links.
Inspect CloudBase Operations Health
by tencentcloudbase
CloudBase teams need a fast way to understand resource health, logs, and service status during incidents. This skill guides Claude, Codex, and Claude Code through read-only inspections and prioritized recommendations.
Diagnose Tilt Dev Environments
by 0xBigBoss
Local Tilt environments can hide failing resources, stale logs, and Docker Compose health problems. This skill guides Claude, Codex, and Claude Code through status checks, logs, and Tiltfile fixes.
Audit Axiom Logs
by Cygnusfear
Production logs can hide urgent errors, noisy warnings, and weak logging practices. This skill queries Axiom, prioritizes issues, and creates an evidence-based audit report.
Build FigJam Plugin Features
by 7nohe
FigJam plugin changes can fail when main-thread and UI APIs are mixed. This skill guides Claude, Codex, and Claude Code through the project structure, build flow, and import workflow.