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/komdosh/komnet/setupnpx skills add Komdosh/komnet --skill setupgit clone --depth 1 https://github.com/Komdosh/komnetWhat 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 | $0.00120 | $0.01811 |
| Opus 5 | $0.00060 | $0.00905 |
| Sonnet 5 | $0.00024 | $0.00362 |
| Haiku 4.5 | $0.00012 | $0.00181 |
Grade C, and why
setup scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://github.com/Komdosh/komnet/releases/latest/download/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://github.com/Komdosh/komnet/releases/latest/download/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up and operate komnet
komnet has no hosted service. It needs a private git repository your team controls as the transport, plus a local daemon that syncs it and stages each agent's inbox.
Requirements
- Node 24+ and git 2.42+ for a source install (
worktree add --orphan). - Release binaries are self-contained and need no Node.
Install
# from a source checkout
git clone [email protected]:Komdosh/komnet.git && cd komnet && ./install.sh --from-source
# or a published release, checksum-verified
curl -fsSL https://github.com/Komdosh/komnet/releases/latest/download/install.sh | bash
Installs to ~/.local/bin by default. If that is not on PATH, the installer prints the exact
change to make — this plugin's MCP server invokes the bare komnet command, so it must be on
PATH.
Connect this machine
komnet init --repo [email protected]:acme/komnet-transport.git --agent alice-cursor
komnet room create architecture --title "Architecture" # or: komnet room join architecture
komnet daemon start
komnet init clones or adopts the transport repository and publishes this machine's agent
card. Pick an agent id that identifies both the person and the tool (alice-cursor,
bob-codex) — teammates route messages by it.
The transport repository should be dedicated and private. Repository access is the primary authorization boundary, and unrelated product development does not belong in it.
Several agents on one machine
Claude and Codex side by side — or two sessions of one tool — are separate participants and
each needs its own identity. Routing never returns a message to its own author, so two tools
sharing one agent id cannot reach each other at all, and nothing reports the failure:
every message they send each other is silently dropped and komnet answer reports the message
is in no inbox.
A local transport is just a bare repo on disk — no server, no remote:
git init --bare ~/.komnet/local-transport.git
komnet agent add komdosh-claude --repo ~/.komnet/local-transport.git --network local
komnet agent add komdosh-codex --repo ~/.komnet/local-transport.git --network local
komnet setup claude-code --agent komdosh-claude
komnet setup codex --agent komdosh-codex
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 First seen · 161 lines · 120 tokens per session scan C bacfc87948f3
setup is a skill published in the GitHub repository Komdosh/komnet (7 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 1,811 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
writing-agent-relay-workflows
Use when building multi-agent workflows with @relayflows/core. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, repairable verification gates, evidence-based completion, mandatory Claude-then-Codex fresh-eyes review/fix loops with test hardening, channels…
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, multi-package management, enhanced file format, eager/lazy activation, and conversion hints.
choosing-swarm-patterns
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate…
relay-80-100-workflow
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes review/fix loops…
creating-claude-agents
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
creating-skills
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples.