Borrowing it
Nothing to install: this file belongs to amxv/agentbox. 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/amxv/agentbox/main/.agents/skills/agentbox-cli-release/SKILL.mdgit clone --depth 1 https://github.com/amxv/agentboxWrote 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/amxv/agentbox/agentbox-cli-release)<a href="https://agentmods.dev/skills/amxv/agentbox/agentbox-cli-release"><img src="https://agentmods.dev/badge/skills/amxv/agentbox/agentbox-cli-release/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/amxv/agentbox/agentbox-cli-release"><img src="https://agentmods.dev/badge/skills/amxv/agentbox/agentbox-cli-release.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 | $0.00077 | $0.02496 |
| Opus 5.5 | $0.00031 | $0.00998 |
| Sonnet 5.5 | $0.00015 | $0.00499 |
| Haiku 4.5 | $0.00008 | $0.00250 |
Grade A, and why
agentbox-cli-release 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 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.
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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentbox CLI Release
Release the Go CLI and its npm wrapper as one versioned unit. Use GitHub Actions by default. Use the manual fallback only when the publish job is cancelled before any step runs because GitHub cannot assign a hosted runner.
Release contract
- Repository:
https://github.com/amxv/agentbox - Go CLI version:
internal/agentbox/version/version.go - npm wrapper version:
packaging/cli/package.json - npm package:
@amxv/agentbox - Release tag:
agentbox-cli-vX.Y.Z - Publish workflow:
.github/workflows/publish-agentbox-npm.yml - Release commit:
chore: release agentbox cli X.Y.Z
The dashboard has its own private package under apps/dashboard; do not change its version for CLI releases. The preparation script requires the Go and npm CLI versions to match.
The generated files under packaging/cli/vendor/ are ignored build artifacts and
must not be committed.
The publish workflow runs CLI tests, builds six binaries, packs and publishes
the npm package with the NPM_TOKEN repository secret, and creates a GitHub
Release for tag pushes matching agentbox-cli-v*. The expected release assets
are:
agentbox-X.Y.Z-darwin-arm64.tar.gzagentbox-X.Y.Z-darwin-amd64.tar.gzagentbox-X.Y.Z-linux-arm64.tar.gzagentbox-X.Y.Z-linux-amd64.tar.gzagentbox-X.Y.Z-windows-arm64.zipagentbox-X.Y.Z-windows-amd64.zipamxv-agentbox-X.Y.Z.tgz
Standard GitHub Actions flow
1. Preflight
Work from a clean main checkout. Preserve unrelated user changes and stop if
the checkout is dirty or has diverged.
git status --short --branch
git fetch origin --tags
git pull --ff-only origin main
git tag --list 'agentbox-cli-v*' --sort=-version:refname | head -20
gh release list --repo amxv/agentbox --limit 10
node -p "require('./packaging/cli/package.json').version"
npm view @amxv/agentbox version dist-tags --json
Choose the next semantic version from the current source change. Confirm that the tag and npm version do not already exist. Before changing versions, inspect the CLI source and tests relevant to the release, then run the release checks:
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 · +4 lines 4b039a9c9c1d
- 2mo ago First seen · 228 lines · 77 tokens per session scan A 3e572305e607
agentbox-cli-release is a skill published in the GitHub repository amxv/agentbox (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,496 once invoked, about $0.0003 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 2026-08-31.
agentbox-cli-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentbox-cli-releaseamxv/agentbox | Skill | 2 | 3d ago | Apache-2.0 | A | 77 | Codex |
| tuturuuu-web-releasetutur3u/platform | Skill | 54 | yesterday | Apache-2.0 | A | 23 | 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 |
| publish-siteNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 19 | Claude Code, Codex |
| create-prmicrosoft/vscode | Skill | 195k | yesterday | MIT | A | 27 | Claude Code, Codex |
| create-draft-prmicrosoft/vscode | Skill | 195k | yesterday | MIT | A | 31 | Claude Code, Codex |