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/dotdevdotdev/agentwire-dev/agentwire-mcp-toolsnpx skills add dotdevdotdev/agentwire-dev --skill agentwire-mcp-toolsgit clone --depth 1 https://github.com/dotdevdotdev/agentwire-devWhat 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 | $0.00087 | $0.03718 |
| Opus 5 | $0.00044 | $0.01859 |
| Sonnet 5 | $0.00017 | $0.00744 |
| Haiku 4.5 | $0.00009 | $0.00372 |
Grade A, and why
agentwire-mcp-tools 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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentWire MCP Tools
Agents running in agentwire sessions should use MCP tools instead of CLI commands. The agentwire MCP server provides tools that wrap CLI functionality. Use these instead of Bash: agentwire <cmd>.
Session Management (13 tools)
| CLI Command | MCP Tool |
|---|---|
agentwire list |
sessions_list() |
agentwire list --context |
sessions_context(session="") — context headroom (remaining %); LOW = bloated. Observe-only (#442). |
agentwire new -s name |
session_create(name="...") |
agentwire send -s name "msg" |
session_send(session="...", message="...") |
agentwire msg send --to name "msg" |
msg_send(to="...", text="...", kind="note", ref="") |
agentwire msg inbox -s name |
msg_inbox(session="...") |
agentwire msg pull -s name |
msg_pull(session="...") |
agentwire msg flush -s name |
msg_flush(session="...") |
agentwire msg dead -s name |
msg_dead(session="...") |
agentwire output -s name |
session_output(session="...") |
agentwire info -s name |
session_info(session="...") |
agentwire kill -s name |
session_kill(session="...") |
agentwire send-keys -s name key1 key2 |
session_send_keys(session="...", keys=["..."]) |
agentwire recreate -s name |
session_recreate(session="...") |
agentwire fork -s name -t project/branch |
session_fork(session="...", target="...") |
agentwire fork -s name -t project/branch --commit abc |
session_fork(session="...", target="...", commit="abc") |
agentwire wait --children |
wait_children(timeout=300) — block on the children YOU spawned; see below |
session_send vs msg_send: session_send pastes + Enter immediately — and clobbers a human's half-typed draft if the box is occupied. Use it only when you must forcibly drive a session now. msg_send is the polite path: it queues a typed message into a file inbox and the watchdog injects it only when the recipient's box is empty and the pane is safe (≤60s). For routine peer updates ("PR drafted", "picking up the footer"), prefer msg_send. kind ∈ note|done|request|escalation|ingest|voice|idle (idle = the idle hook's synthetic placeholder for a child that went quiet without reporting, #952 — never hand-send it); to="@all" broadcasts to live agent sessions except you. See wiki sessions/messaging.md.
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.
- yesterday First seen · 186 lines · 87 tokens per session scan A ad08505ca247
agentwire-mcp-tools is a skill published in the GitHub repository dotdevdotdev/agentwire-dev (21 stars, last pushed 17d ago), licensed Apache-2.0. It adds 87 tokens to every session and 3,718 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
luvus-module
Write a luvus module (an extension for luvus, mission control for your AI coding agents). Use when the user is building or debugging a luvus module: authoring luvus-module.toml, adding a sidebar dock, Luvus Bar widget, right-click action, event hook, module pane, module settings, or calling luvus back over its UHP.
luvus
Control Luvus through its local CLI and UHP. Use only for a line beginning with =target message, an explicit request naming Luvus, a request to delegate to a named live Luvus agent or pane, or an explicit Luvus operation involving sessions, workspaces, tabs, panes, agents, files, Git, DIFF, worktrees, tasks, leases…
tmux-via-mcp
Use the tmux MCP tools to create sessions, shape layouts, run tracked commands, and automate interactive terminals when a real TTY or parallel panes are required.
tmux-buffer-explorer
Explore large tmux buffers via search and bounded slices. Use when buffer data is too large to load at once or needs incremental inspection.
not-happy-jan
Adjust Not-Happy-Jan feedback settings by running the nhj CLI when the user wants to tune voices, dials, muting, censoring, tests, or hold music.
release
Use when the user asks to release unitmux, bump the version, publish a GitHub release, update the Homebrew cask, check release status, or says リリース/release/バージョン上げて.