agentmods.dev

beaker-usage

beaker-usage is a skill for Claude Code, Codex from rilixai/beaker-skill. It costs 95 tokens per session (3,890 once invoked), scanned A, original, MIT.

An operational skill for using an already-configured Beaker integration to run and monitor agent optimization over a repository or other editable resource. Beaker is the connected service used for those optimization runs.

In plain words
What is it for?
Use it to choose a GitHub branch or dataset, launch a run, compare models when supported, inspect run status, and retrieve results.
Why use it?
It guides setup checks, launch preparation, environment validation, status monitoring, and result inspection without changing the project itself.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: $skill-name invocation.

Part of the beaker plugin — 2 skills shipped together

not rated 5repo changed 7d ago A scan SkillSpector: warn 95 tokens original MIT

Good fit Use it to choose a GitHub branch or dataset, launch a run, compare models when supported, inspect run status, and retrieve results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rilixai/beaker-skill/beaker-usage
View source ↗ rilixai/beaker-skill withbeaker.ai
Install

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.

Any agent
npx skills add rilixai/beaker-skill --skill beaker-usage
Clone the repo
git clone --depth 1 https://github.com/rilixai/beaker-skill

Made for: Claude Code, Codex.

Or install beaker, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for beaker-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/rilixai/beaker-skill/beaker-usage/github.svg)](https://agentmods.dev/skills/rilixai/beaker-skill/beaker-usage)
Your own site
<a href="https://agentmods.dev/skills/rilixai/beaker-skill/beaker-usage"><img src="https://agentmods.dev/badge/skills/rilixai/beaker-skill/beaker-usage/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.

agentmods 80×15 button for beaker-usage

Your own site · 80×15
<a href="https://agentmods.dev/skills/rilixai/beaker-skill/beaker-usage"><img src="https://agentmods.dev/badge/skills/rilixai/beaker-skill/beaker-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,890 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 22
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Excessive Agency · line 43
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.03890
Opus 5.5 $0.00038 $0.01556
Sonnet 5.5 $0.00019 $0.00778
Haiku 4.5 $0.00010 $0.00389

Measured 7d ago against content hash 17fd7042a344, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

beaker-usage scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Never expose secrets or bypass the CLI with `curl` or private API calls.
skills/beaker-usage/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beaker usage

Operate the repository's connected Beaker integration through the beaker CLI. Keep this workflow operational: do not edit the integration, application, tests, datasets, CI/CD automation, or Beaker config merely to launch or manage a run.

Version check

This skill (0.6.6) is written for beaker-sdk 0.6.6; skill and SDK share one version number and release together. Run beaker --version first. If the CLI is older than 0.6.6 or does not recognize --version, upgrade beaker-sdk through the project's development-dependency workflow. If it is newer than 0.6.6, run npx skills update beaker-usage and npx skills update beaker-setup, then reload the skill before continuing.

Read cli-reference.md when constructing a launch, interpreting status exit codes, pulling results, or handling a CLI error.

During setup validation and launch preparation:

  • Run beaker onboarding status at the start of the flow and after a completed onboarding step, not after read-only probes, then follow its returned action.
  • Relay only newly discovered actions in blocked_on_developer verbatim to the developer without attempting developer-owned work, tracking what was already reported in this session. Batch the currently known actions, ask the developer to begin them immediately, and continue with the returned next.action so their work overlaps with yours. Do not perform integration_pushed while dataset_available or required_env_configured is incomplete; wait once no earlier agent work remains.
  • An unknown step has not been checked yet and never means the developer must act. Stop and wait only when next itself is developer-owned.
  • Complete dataset_available and required_env_configured before integration_pushed, the final blocking agent-owned step. Commit and push the completed integration once, without asking the developer to confirm unless they told you not to take autonomous actions, to a beaker/<YYYYMMDD-HHMM>-<agent-name> branch in the selected agent repository before a hosted optimization run. The agent normally completes dataset selection and experiment_launched too, but the developer may also complete them through the platform UI.
  • Tracing is optional: if it applies, make a best effort to include it in that push, but never let it block the push; never commit secret files.

Read the full file on GitHub · 372 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 7d ago Changed · +22 lines · +4 tokens per session 17fd7042a344
  2. 20d ago Changed · +2 lines 5838a98601cc
  3. 1mo ago Changed 654ee42b13ad
  4. 1mo ago Changed 8174e3863b0e
  5. 1mo ago Changed a95f4f1c778e
  6. 1mo ago Changed df5d724747ce
  7. 1mo ago Changed 5b83c4123756
  8. 1mo ago Changed d8a1ac45a06a
  9. 2mo ago Changed · -49 lines 0c596cf9e80d
  10. 2mo ago First seen · 397 lines · 91 tokens per session scan A 1ce175d62ae1

Subscribe to this mod's changes

beaker-usage is a skill published in the GitHub repository rilixai/beaker-skill (5 stars, last pushed 8d ago), licensed MIT. It adds 95 tokens to every session and 3,890 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics
Related

beaker-usage compared with skills from other repositories

beaker-usage next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
beaker-usagerilixai/beaker-skillSkill58d agoMITA95Claude Code, Codex
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill316k8d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code