AlphaClaw is a browser-based management layer for OpenClaw, an AI-agent gateway, that guides setup and monitors running agents. It helps users configure multiple agents, manage integrations, recover gateway failures, and observe activity from one dashboard.
Borrowing it
Nothing to install: this file belongs to chrysb/alphaclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrysb/alphaclaw/main/.agents/skills/release-beta/SKILL.mdgit clone --depth 1 https://github.com/chrysb/alphaclawWrote 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/chrysb/alphaclaw/release-beta)<a href="https://agentmods.dev/skills/chrysb/alphaclaw/release-beta"><img src="https://agentmods.dev/badge/skills/chrysb/alphaclaw/release-beta/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/chrysb/alphaclaw/release-beta"><img src="https://agentmods.dev/badge/skills/chrysb/alphaclaw/release-beta.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00509 |
| Opus 5.5 | $0.00010 | $0.00204 |
| Sonnet 5.5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
release-beta 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 2mo 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.
What it actually says
Release Beta
Use this workflow whenever the user asks to "publish beta", "push beta channel", "cut another beta", or equivalent.
Goal
Ship a new @chrysb/alphaclaw beta and keep
~/Projects/openclaw-railway-template beta branch pinned to that exact beta
version.
Required sequence
-
Prepare commit state in AlphaClaw
- Check
git status --shortin~/Projects/alphaclaw. - If there are changes to include, stage and commit them first.
- Never commit unrelated secret files.
- Check
-
Run tests before release
- Run
npm testin~/Projects/alphaclaw. - Abort beta publish if tests fail.
- Run
-
Cut and publish beta
npm version prerelease --preid=betagit push && git push --tagsnpm publish --tag beta
-
Always update Railway beta template pin (mandatory)
- Open
~/Projects/openclaw-railway-template/package.json. - Ensure branch is
beta. - Set
"@chrysb/alphaclaw"to the exact new beta version (for example"0.7.2-beta.1"). - If you updated dependency pins (for example
openclaw), runnpm installin the template repo sopackage-lock.jsonis refreshed before committing. - Commit and push that repo:
- commit message format:
Pin AlphaClaw beta to <version>. - push to
origin/beta.
- commit message format:
- Open
-
Report completion
- Include:
- release commit hash in AlphaClaw
- beta tag/version published
- Railway template commit hash for the pin update
- Mention any warnings (for example npm
package.jsonnormalization warning).
- Include:
Safety notes
- Do not skip tests unless user explicitly asks.
- Do not use
--no-verify. - Do not force push.
- Do not create GitHub release notes for beta-only publishes unless requested.
- Prefer deterministic installs in templates: keep
package-lock.jsoncommitted and usenpm ciin Dockerfiles.
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.
- 2mo ago First seen · 62 lines · 25 tokens per session scan A 76758e64390c
release-beta is a skill published in the GitHub repository chrysb/alphaclaw (1,479 stars, last pushed 14d ago), licensed MIT. It adds 25 tokens to every session and 509 once invoked, about $0.0001 per session on Opus 5.5. 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.
release-beta compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-betachrysb/alphaclaw | Skill | 1.5k | 14d ago | MIT | A | 25 | Claude Code, Codex |
| draft-release-notesprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 174 | Claude Code, Codex |
| publish-npm-versionprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 182 | Claude Code, Codex |
| shipGCWing/BitFun | Skill | 2.1k | 2mo ago | MIT | A | 105 | Claude Code, Codex |
| installxiaotonng/pikiloom | Skill | 293 | 4d ago | MIT | A | 39 | Claude Code, Codex |
| pm-releasekonglong87/superPM | Skill | 86 | 11d ago | MIT | A | 60 | Claude Code |
| ensemble-releaseFortiumPartners/ensemble | Skill | 12 | yesterday | MIT | A | 27 | Claude Code, Codex |