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 LilithGames/a2wave --skill a2wave-cligit clone --depth 1 https://github.com/LilithGames/a2waveWrote 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/lilithgames/a2wave/a2wave-cli)<a href="https://agentmods.dev/skills/lilithgames/a2wave/a2wave-cli"><img src="https://agentmods.dev/badge/skills/lilithgames/a2wave/a2wave-cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lilithgames/a2wave/a2wave-cli"><img src="https://agentmods.dev/badge/skills/lilithgames/a2wave/a2wave-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00098 | $0.05086 |
| Opus 5.5 | $0.00039 | $0.02034 |
| Sonnet 5.5 | $0.00020 | $0.01017 |
| Haiku 4.5 | $0.00010 | $0.00509 |
Grade C, and why
a2wave-cli scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Never suggest raw `docker compose down -v` / `rm -rf` for uninstalling an a2wave install — the setup command's gates exist to prevent destroying unrelated projects. How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a2wave CLI
Use the a2wave command-line tool to manage the a2wave Agent orchestration platform.
Checks Before You Start
- Before debugging authentication, URL, token, or backend connectivity issues, run
a2wave statusfirst. - If the URL is not yet configured, set it with
a2wave config set-url <url>; you can also pass--url <url>on a single command, or setA2WAVE_URL. - Login and URL configuration are two separate things:
a2wave loginruns OAuth SSO via your identity provider (IdP) and writes local credentials. - For resource arguments that accept
<id|name>, you can pass an ID or an exact name; an ID is used directly, while a name is resolved via the list API.
Platform Install (setup)
a2wave setup --image a2wave:latest # interactive: dir + port prompts, then docker compose up + health wait
a2wave setup --yes --image a2wave:latest # non-interactive with defaults (~/a2wave, port 3502)
a2wave setup --yes --image a2wave:latest --dir /srv/a2wave --port 3510 --base-url http://192.168.1.10:3510
a2wave setup --no-start --image a2wave:latest # generate .env + docker-compose.yml only
a2wave setup --yes --database-url postgres://a2wave:[email protected]:5432/a2wave # EXPERIMENTAL: external PostgreSQL backend
a2wave setup --yes --with-postgres # EXPERIMENTAL: bundle a postgres:16-alpine sidecar (password generated into .env)
a2wave setup --upgrade --image a2wave:1.4.0 # move an existing install to a new image, keeping its data
a2wave setup --down # uninstall: requires typing the install dir path to confirm
a2wave setup --reset-password # forgot the admin password: reset it from a running install
--upgradeis the only supported way to move an install to a new image — never tell a user to hand-editdocker-compose.yml. The image lives in.envasA2WAVE_IMAGE(the compose file reads it via${A2WAVE_IMAGE:-...}), so the upgrade rewrites one env key, backs the data volume up toa2wave-data-<stamp>.tar.gzin the install dir first (--no-backupskips it), then pulls and recreates only the a2wave service and waits for liveness and readiness. It never deletes the data volume, and everything else in.envsurvives byte-for-byte. A legacy install with a hardcoded image line is migrated to the variable automatically when the file still matches the generated layout; a hand-edited compose file is refused with the exact edit to make rather than guessed at. If the new image fails to start or fails its checks, the previous image is restored, brought back up, and health-verified before the rollback is reported as successful. Cannot be combined with--down,--reset-password,--base-url,--port, or--no-start.
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.
- 1mo ago Changed · +3 lines f6d004e98fb7
- 1mo ago First seen · 305 lines · 98 tokens per session scan C e3aa10e447e7
a2wave-cli is a skill published in the GitHub repository LilithGames/a2wave (27 stars, last pushed yesterday), licensed Apache-2.0. It adds 98 tokens to every session and 5,086 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…