Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Komdosh/komnet/plugin install komnet-gatewayWrote 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/consult)<a href="https://agentmods.dev/commands/komdosh/komnet/consult"><img src="https://agentmods.dev/badge/commands/komdosh/komnet/consult/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/consult"><img src="https://agentmods.dev/badge/commands/komdosh/komnet/consult.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 | $0.00031 | $0.00855 |
| Opus 5.5 | $0.00012 | $0.00342 |
| Sonnet 5.5 | $0.00006 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
consult 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.
Answer a question about the product or about work happening on other machines by
consulting the agents that actually know, through this machine's komnet relay
gateway. Load the komnet-gateway:reach-out skill first.
Question: $ARGUMENTS
This is the read-the-room command: it asks, waits, and reports. Use
/komnet-gateway:ask instead for a single fire-and-forget message.
1. Answer locally first, and say what is missing
Before sending anything, establish what you already know from this repository, its git history, and its docs. State that part of the answer plainly.
Then identify what genuinely is not knowable here — the state of another service, someone else's progress, a decision made elsewhere. Only that goes to the network. If nothing does, answer the user and stop; do not send a message to confirm something you can already see.
2. Find the gateway and the rooms
ListAgents → find the gateway peer (conventionally komnet-gateway). Not
running: tell the user the network cannot be consulted right now, give the local
answer, and stop.
Ask the gateway which rooms exist if you do not know, or run
komnet rooms 2>/dev/null / komnet status --json if komnet is on PATH here.
Do not guess room names — an unroutable message is held, not delivered.
3. Ask
Compute this project's key:
printf '%s' "${CLAUDE_PROJECT_DIR:-$PWD}" | cksum | cut -d' ' -f1
Send one question per room that genuinely owns part of the answer — usually one, rarely more than three. Each is a permanent, team-visible message, so make it specific and self-contained; the agent reading it has none of your context.
Use the envelope in the reach-out skill, over SendMessage when the gateway is
listed, or as a request file when it is not.
4. Wait, bounded
If this session is reachable (it appears in ListAgents): the answers arrive
on their own as cross-session messages. Tell the user you asked, give the local
answer now, and stop. Do not poll.
If it is not reachable: the gateway cannot push, so wait on the reply files.
Run with Bash run_in_background — never in the foreground:
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 · 31 tokens per session scan A d9fe9dc78305
consult is a command published in the GitHub repository Komdosh/komnet (8 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 855 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.
consult compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| consultKomdosh/komnet | Command | 8 | 2d ago | MIT | A | 31 | 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 |