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/wikinpx skills add dotdevdotdev/agentwire-dev --skill wikigit 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 | $0.00092 | $0.01887 |
| Opus 5 | $0.00046 | $0.00944 |
| Sonnet 5 | $0.00018 | $0.00377 |
| Haiku 4.5 | $0.00009 | $0.00189 |
Grade A, and why
wiki 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentWire Wiki
LLM-maintained knowledge base at ~/.agentwire/wiki/. Read ~/.agentwire/wiki/CLAUDE.md for the full schema and conventions.
How the loop actually works: authoring is in-context — the session that learns something writes the page itself (Write/Edit into wiki/<category>/<name>.md), with full context, for free. That's the working path; there is no scheduled batch ingester. The mechanical parts — searching, health-checking, scaffolding, archiving sources — are deterministic and run through the agentwire wiki CLI (and the wiki_query / wiki_lint / wiki_status MCP tools), exactly like /handoff splits "LLM distills in-context, CLI renders deterministically."
| Mechanical op | Command |
|---|---|
| Search the wiki | agentwire wiki query <q> [--limit N] [--json] / MCP wiki_query |
| Health-check (structural + ground-truth) | agentwire wiki lint [--strict] [--json] / MCP wiki_lint |
| Overview (counts, unprocessed raw, health) | agentwire wiki status [--json] / MCP wiki_status |
| Scaffold a page with correct frontmatter | agentwire wiki new <category> <name> [--title T] |
| Archive a consumed source | agentwire wiki done <rawfile> |
(All stdlib-only — they run from a source checkout with no rebuild.)
Subcommands
/wiki ingest
Authoring is in-context and primary. When you discover something worth keeping, write or update the page now, in your own session — agentwire wiki new <category> <name> scaffolds the frontmatter, then you fill in the body and add [[page-name]] wikilinks. This is how the wiki is maintained; don't wait for a batch job (there isn't one).
raw/ is an optional verbatim-source inbox — a place to stash an article, gist, transcript, or findings dump you might author from later. It is not the primary path and nothing drains it automatically.
To author from a stranded raw source:
- Read the file in
raw/. - Identify entities (technologies, patterns, APIs, research topics) and, for each, create (
agentwire wiki new …) or update the matchingwiki/<category>/<name>.md— in-context, citing the raw file as a source. - Add
[[page-name]]wikilinks for cross-references. - When the source is consumed, archive it:
agentwire wiki done <rawfile>movesraw/<f>→raw/processed/<f>(content is never edited — only relocated, so immutability holds; "unprocessed = files directly inraw/" stays a trivial check, no.ingestedmarker).
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 · 106 lines · 92 tokens per session scan A 11d5844918af
wiki is a skill published in the GitHub repository dotdevdotdev/agentwire-dev (21 stars, last pushed 17d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,887 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.