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 skills add am-will/limux --skill limux-a2agit clone --depth 1 https://github.com/am-will/limuxWrote 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/skills/am-will/limux/limux-a2a)<a href="https://agentmods.dev/skills/am-will/limux/limux-a2a"><img src="https://agentmods.dev/badge/skills/am-will/limux/limux-a2a.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.02055 |
| Opus 5 | $0.00025 | $0.01027 |
| Sonnet 5 | $0.00010 | $0.00411 |
| Haiku 4.5 | $0.00005 | $0.00205 |
Grade A, and why
limux-a2a scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Limux A2A
Use Limux itself as the live registry. Do not rely on generated files or persistent rosters. Prefer the installed limux command; use ./target/.../limux-cli only when testing this repo build.
Fast Launch
When asked to launch a peer from inside Limux, split first using the already-exported LIMUX_* values. Do not run identify, list-workspaces, or read-screen before the first spawn unless an env value is missing.
created="$(limux --json new-pane \
--workspace "$LIMUX_WORKSPACE_ID" \
--pane "$LIMUX_PANE_ID" \
--surface "$LIMUX_SURFACE_ID" \
--direction right \
--command 'claude "Task prompt here. Parent surface if you need it: '"$LIMUX_SURFACE_ID"'."')"
child_surface="$(printf '%s\n' "$created" | jq -r '.surface_ref // .surface_id' | sed 's/^surface://')"
child_pane="$(printf '%s\n' "$created" | jq -r '.pane_ref // .pane_id' | sed 's/^pane://')"
If the fast launch fails with failed to connect to socket, retry that exact new-pane command with approved/escalated socket access. If it fails with Unknown option --json, switch to the repo-built ./target/debug/limux-cli or ./target/release/limux-cli and retry the same command. Only after those retries should you inspect socket/listing state.
Identity
Each Limux terminal should have:
printf 'workspace=%s\npane=%s\nsurface=%s\ntab=%s\nsocket=%s\n' \
"$LIMUX_WORKSPACE_ID" "$LIMUX_PANE_ID" "$LIMUX_SURFACE_ID" "$LIMUX_TAB_ID" "$LIMUX_SOCKET"
Fallbacks:
limux --json identify
limux --json list-workspaces
limux --json list-panels --workspace "$LIMUX_WORKSPACE_ID"
Target exact peers with --surface <surface-id>. Add --workspace <id-or-name> when the peer is outside the current workspace.
Spawn Panes
Launch tools directly with new-pane --command; do not create an empty shell and later inject a long escaped codex "..." line. Long injected launch lines can wrap or corrupt the shell input.
created="$(limux --json new-pane \
--workspace "$LIMUX_WORKSPACE_ID" \
--pane "$LIMUX_PANE_ID" \
--surface "$LIMUX_SURFACE_ID" \
--direction right \
--command 'codex "Task: inspect the diff. Parent surface available if needed: '"$LIMUX_SURFACE_ID"'."')"
child_surface="$(printf '%s\n' "$created" | jq -r '.surface_ref // .surface_id' | sed 's/^surface://')"
child_pane="$(printf '%s\n' "$created" | jq -r '.pane_ref // .pane_id' | sed 's/^pane://')"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 179 lines · 50 tokens per session scan A 5a274bcdf5f6
limux-a2a is a skill published in the GitHub repository am-will/limux (549 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,055 once invoked, about $0.0003 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.