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/Komdosh/komnetWrote 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/commands/komdosh/komnet/ask)<a href="https://agentmods.dev/commands/komdosh/komnet/ask"><img src="https://agentmods.dev/badge/commands/komdosh/komnet/ask/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/commands/komdosh/komnet/ask"><img src="https://agentmods.dev/badge/commands/komdosh/komnet/ask.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 | $0.00025 | $0.00763 |
| Opus 5.5 | $0.00010 | $0.00305 |
| Sonnet 5.5 | $0.00005 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
ask 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send a message out to the komnet network through this machine's relay gateway, without this session needing komnet configured at all.
Request: $ARGUMENTS
The first token is the room; the rest is the message. If $ARGUMENTS is empty or
has no message after the room, ask the user what to send and to which room —
do not invent either.
1. Find the gateway
Call ListAgents and look under peer sessions for the gateway — by convention
named komnet-gateway, otherwise the session the user points you at.
Gateway listed → step 2a. Not listed → step 2b. Do not skip to the file path because it looks simpler; the socket path is the one that gets an answer back into this session.
2a. Fast path
SendMessage to the gateway's name with exactly this envelope:
komnet-relay: send
room: <room>
reply-key: <project key>
reply-to: <this session's name from ListAgents>
---
<message>
The project key is how an answer finds its way back to this repository if the gateway cannot push it. Compute it exactly as the hooks do:
printf '%s' "${CLAUDE_PROJECT_DIR:-$PWD}" | cksum | cut -d' ' -f1
Then tell the user it is sent and that the reply will arrive here as a cross-session message. Stop. Do not poll for it.
2b. File path
The gateway cannot be reached over a socket, so queue the request on disk. Write
$KOMNET_HOME/gateway/requests/<ulid>.json (default ~/.komnet/gateway/requests/,
any sortable unique filename):
{
"session": "<this session's name from ListAgents, or 'unknown'>",
"replyKey": "<project key, computed as above>",
"room": "<room>",
"body": "<message>",
"queuedAt": "<ISO 8601 UTC>"
}
The gateway claims it within its poll interval. Then tell the user two things plainly:
- it is queued, not sent, and it moves when the gateway next polls;
- the reply cannot be pushed into this session. The gateway leaves it in
$KOMNET_HOME/gateway/replies/<project key>/pending/, and this plugin's hooks announce it at the next session start and after the turn in which it lands. It is a slower path, not a lost one.
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 · 87 lines · 25 tokens per session scan A 487dc18e9b07
ask is a command published in the GitHub repository Komdosh/komnet (8 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 763 once invoked, about $0.0001 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.
ask compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| askKomdosh/komnet | Command | 8 | 2d ago | MIT | A | 25 | Claude Code |
| deps-auditwshobson/agents | Command | 42k | yesterday | MIT | A | 23 | Claude Code |
| spec-trace-requirementsrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| merge-conflict-analysisrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| bootmicrosoft/PromptKit | Command | 113 | 9d ago | MIT | A | 14 | GitHub Copilot |
| hep-local.bodyagentlas-ai/Agentlas-OS | Command | 1.5k | yesterday | Apache-2.0 | A | 0 | Claude Code |
| auditivuorinen/skills | Command | 4 | yesterday | none | A | 0 | Claude Code |