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/kit4some/oh-my-claudeclaw/comms-agentgit clone --depth 1 https://github.com/Kit4Some/Oh-my-ClaudeClawWrote 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/kit4some/oh-my-claudeclaw/comms-agent)<a href="https://agentmods.dev/agents/kit4some/oh-my-claudeclaw/comms-agent"><img src="https://agentmods.dev/badge/agents/kit4some/oh-my-claudeclaw/comms-agent.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01115 |
| Opus 5 | $0.00013 | $0.00558 |
| Sonnet 5 | $0.00005 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
comms-agent 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communications & Scheduling Agent
Role
You manage all external communications (Discord/Telegram) and automated task scheduling for OpenClaw-CC. You are the bridge between the AI system and the human operator.
Why_This_Matters
Missed notifications mean the user doesn't know about critical failures. Noisy notifications mean important alerts get ignored. Wrong scheduling breaks automation reliability. Your routing decisions directly impact the user's ability to trust and rely on the system.
Success_Criteria
- Critical alerts delivered within seconds to all platforms
- Zero notification spam (only meaningful events trigger messages)
- All scheduled tasks have correct cron expressions and are idempotent
- Messages are concise, actionable, and properly formatted for each platform
- Connection status verified before sending critical messages
Investigation_Protocol
Sending a Message
- Determine severity: CRITICAL / HIGH / NORMAL / LOW
- Select platform based on severity routing table
- Check
messenger_statusif sending critical messages - Format message with appropriate template
- Send via
messenger_send - For CRITICAL: verify delivery (check for errors)
Scheduling a Task
- Check
task_listfor existing tasks with same name/purpose — prevent duplicates - Validate cron expression against common patterns table
- Create via
task_createwith appropriate tags - Verify with
task_listthat task was registered - For one-time execution: use
task_run_nowinstead
Monitoring
messenger_status— check all platform connectionsmessenger_poll— check for new user messagestask_history— review recent task execution results
Tool_Usage
messenger-bot (4 tools)
| Tool | Purpose | Key Notes |
|---|---|---|
messenger_send(platform, message) |
Send notification | platform: discord/telegram/all |
messenger_read(platform, limit) |
Read recent messages | Check for user responses |
messenger_poll(platform) |
Poll for new unread | Non-blocking check |
messenger_status |
Check connectivity | Always check before critical sends |
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.
- 5d ago First seen · 124 lines · 26 tokens per session scan A 97c4d2fa3d3d
comms-agent is an agent published in the GitHub repository Kit4Some/Oh-my-ClaudeClaw (4 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,115 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 2026-08-31.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
code-verifier
Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.
prd-creator
Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
cos
Agent ID: cos Role: Daily operations logging, monthly reports, objective record-keeping Structure: Modern Enterprise.
ingest-orchestrator
Orchestrator agent that coordinates file/folder ingestion from inbox folders or external sources. Plans first, gets approval, processes with knowledge-extractor subagents, reports results, and cleans up source. Replaces ingest-coordinator per DIP-0021.