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 skills/nikolamin/claude-coordinator-kit/comms-registernpx skills add nikolamin/claude-coordinator-kit --skill comms-registergit clone --depth 1 https://github.com/nikolamin/claude-coordinator-kitWrote 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/skills/nikolamin/claude-coordinator-kit/comms-register)<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/comms-register"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/comms-register.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 5.1 | $0.00219 | $0.01017 |
| Opus 5 | $0.00110 | $0.00508 |
| Sonnet 5 | $0.00044 | $0.00203 |
| Haiku 4.5 | $0.00022 | $0.00102 |
Grade A, and why
comms-register 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.
What it actually says
Comms register
Lead with the actionable fact. Status answers look like: "Yes. 1 agent running: X. Queued next: Y. Nothing needs you." — direct answer, counts not prose, one line per fact, close with whether the user is needed. Save narrative framing for genuinely new decisions that need context. The notify channel is typically read on a phone — keep messages short and plain text, no markdown tables or wide output.
Notifications on <NOTIFY_CHANNEL>:
- Checkpoint ping when a batch of work closes and pushes (batch-level, not per-task).
- Immediate ping the moment something genuinely needs the user (blocking decision, required live playthrough, escalation) — don't wait for the next checkpoint.
- One ask per ping. Maintain a queue if multiple items need attention; send the top one,
wait for resolution, send the next. Checkpoint pings stay status-only — don't tack on a
request list. This is
coordinator-kit:question-protocolapplied over the notify channel specifically. - Never put a backtick in a notify message body. A double-quoted
notify.sh "..."call is still a shell command line — backtick-wrapped text inside it triggers bash command substitution and can execute the embedded text instead of just displaying it. On Windows (PowerShell), backtick is the escape character and$nameexpands inside a double-quoted string too, so a notify body there must contain neither a backtick nor a$. Describe commands in prose, or write the literal text to a file in.coordinator-scratch/and reference its path instead of quoting it inline.
If the Telegram bridge is installed (at <BRIDGE_DIR> — see <BRIDGE_DIR>/SETUP.md) and
<NOTIFY_CHANNEL> is it: on Windows substitute the .ps1 of the same name, invoked via
powershell -ExecutionPolicy Bypass -File.
- Arm a persistent Monitor on
<BRIDGE_DIR>/relay-inbox.jsonlat session start — create the file first if it doesn't exist yet (touch, orNew-Item -ItemType Fileon Windows), since it's gitignored and only created once the first message actually arrives; a Monitor armed on a missing file has nothing to watch. Founder messages arrive mid-session, into this same running context, not via a separate headless process. Re-arm it if the session is ever resumed. - Signal "still working" via
<BRIDGE_DIR>/typing.sh [seconds]as soon as a relayed message is picked up but a reply isn't ready yet — the initial acknowledgment reaction alone gives no progress signal on a long turn. - Reply via
<BRIDGE_DIR>/notify.sh "<text>". - Acknowledge each relayed message with
<BRIDGE_DIR>/react.sh <message_id> ok|fail(sets the final ok/fail reaction, replacing the bot's initial acknowledgment). - Deliver file deliverables via
<BRIDGE_DIR>/send-file.sh <path> [caption](see<BRIDGE_DIR>/SETUP.md) — a file produced in the session UI does not reach the notify channel on its own. Run it as an ordinary script, same asnotify.sh/react.sh— never hand-roll a raw API call against the notify channel's provider directly; that would collide with the installedCLAUDE.md's Role section investigative-Bash prohibition and go around this narrow notification-sending exception.
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 Changed · +3 lines bd69eb513b08
- 5d ago First seen · 58 lines · 219 tokens per session scan A ba4049dc1a95
comms-register is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 3d ago), licensed MIT. It adds 219 tokens to every session and 1,017 once invoked, about $0.0011 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…