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-schedulernpx skills add dotdevdotdev/agentwire-dev --skill agentwire-schedulergit 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 | $0.00103 | $0.01573 |
| Opus 5 | $0.00051 | $0.00787 |
| Sonnet 5 | $0.00021 | $0.00315 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
agentwire-scheduler 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentWire Scheduler
Scheduler Task Gates
Tasks in ~/.agentwire/scheduler.yaml can define gate preconditions to skip execution when changes aren't relevant:
tasks:
code-quality:
gate:
git_commit: true # Skip if HEAD unchanged since last run
doc-drift:
gate:
git_diff: # Skip if no commits touched these paths
- docs/
- agentwire/
custom-check:
gate:
command: "test -f /tmp/ready.flag" # Skip if command exits non-zero
Gates are evaluated before dispatching and skip the task (zero AI cost) if conditions fail. Multiple gates are AND'd. Gates fail open on errors.
Worktree + PR Mode (the standard for repo work)
Tasks that touch a git repo run in an isolated worktree forked off the latest base branch, and their output is proposed back as a draft PR — the live project folder is never modified and nothing lands on main unreviewed.
tasks:
doc-drift:
project: ~/projects/agentwire-dev
worktree: true # DEFAULT when project is a git repo
base: main # fork the worktree off latest origin/main
pr_target: main # draft PR base branch (defaults to `base`)
pr_draft: true # open as draft (default)
ai-morning-briefing:
project: ~/projects/agentwire-dev
worktree: false # research/email task — runs in place, never commits
| Field | Default | Meaning |
|---|---|---|
worktree |
auto (true if project is a git repo) |
Run isolated + open a PR. Set false for tasks that only email/produce side effects. |
base |
main |
Branch the worktree forks from (fetched fresh from origin). |
pr_target |
base |
PR base branch. |
pr_draft |
true |
Open the PR as a draft. |
Lifecycle: branch scheduler-<task>-<timestamp> → run in worktree → if it produced changes, git add -A + commit (scheduler: <task> — <summary>) + push + draft PR; if it produced nothing, the empty worktree is removed and no PR is opened. The worktree persists while the PR is open (so you can spawn a session there during review) and is reaped automatically when the PR merges or closes (worktree + branch + session torn down). worktree: false tasks run in place and never commit.
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 · 134 lines · 103 tokens per session scan A 95aff66eb347
agentwire-scheduler is a skill published in the GitHub repository dotdevdotdev/agentwire-dev (21 stars, last pushed 17d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,573 once invoked, about $0.0005 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.