Borrowing it
Nothing to install: this file belongs to chankov/agent-fleet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chankov/agent-fleet/main/.pi/agent-fleet/hermes/skills/hub-liaison/SKILL.mdgit clone --depth 1 https://github.com/chankov/agent-fleetWrote 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/chankov/agent-fleet/hub-liaison)<a href="https://agentmods.dev/skills/chankov/agent-fleet/hub-liaison"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/hub-liaison/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/skills/chankov/agent-fleet/hub-liaison"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/hub-liaison.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00059 | $0.01042 |
| Opus 5.5 | $0.00024 | $0.00417 |
| Sonnet 5.5 | $0.00012 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
hub-liaison scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hub Liaison
Overview
You are the gateway-side liaison between a human Telegram reply and the pi user-remote coms peer. When a Telegram message correlates to a hub question marker, write one answer file for the bridge. Do not answer by paraphrasing in chat only; the bridge only consumes the file.
When to Use
Use this skill when an incoming Telegram message either:
- replies to a message that contains
[HUB-Q:<qid>], or - contains the explicit prefix
HUB-Q:<qid>:.
<qid> must be a 26-character Crockford ULID matching:
^[0-9A-HJKMNP-TV-Z]{26}$
Ignore non-matching messages. If a message is ambiguous and there is more than one plausible question marker, ask the human to reply to the original question or use HUB-Q:<qid>: <answer>.
Correlation Rules
- Prefer the qid from the replied-to message marker:
[HUB-Q:<qid>]. - If there is no replied-to marker, accept a message prefix exactly shaped as
HUB-Q:<qid>: <answer>. - The answer text is the Telegram reply body, except for prefix-form messages where the answer text is everything after
HUB-Q:<qid>:. - Preserve the human's answer text exactly except for trimming leading/trailing whitespace around the extracted answer.
- Never invent or alter the qid. If the qid does not match the regex above, do not write a file.
- If a human message contains or replies to a
[HUB-Q:<qid>]question, write the answer file even when the thread also contains a cancel/closed note or the user appears to be answering after cancellation. Do not decide whether the question is still open; the bridge validates pending vs. late and sends the appropriate polite closed note.
Process
- Extract
<qid>and<answer>using the correlation rules. - Confirm
<answer>is non-empty. If it is empty, ask the human for the answer text. - Do not suppress the write because the question appears canceled, closed, timed out, or answered locally. That state belongs to the bridge, not this skill.
- Write exactly this file path, replacing
<qid>with the extracted qid:
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.
- 2mo ago First seen · 85 lines · 59 tokens per session scan A db710aa934f3
hub-liaison is a skill published in the GitHub repository chankov/agent-fleet (20 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 1,042 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 2026-09-03.
hub-liaison compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hub-liaisonchankov/agent-fleet | Skill | 20 | 12d ago | MIT | A | 59 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |