What is self-verify-beacon-in-sandbox?

A testing workflow for Beacon, a telemetry tool, that runs a real Claude Code session inside a temporary Linux cloud computer and checks what Beacon recorded.

Use it to check Beacon changes from start to finish, validate telemetry capture, and interpret test results from disposable cloud environments.

It shows whether a Beacon change works in a real session, not just whether the code compiles. It also helps distinguish Beacon problems from setup or sandbox failures.

How Asymptote-Labs/agent-beacon configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Asymptote-Labs/agent-beacon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Asymptote-Labs/agent-beacon/main/.claude/skills/self-verify-beacon-in-sandbox/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Asymptote-Labs/agent-beacon

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/self-verify-beacon-in-sandbox/github.svg)](https://agentmods.dev/skills/asymptote-labs/agent-beacon/self-verify-beacon-in-sandbox)

Your own site

<a href="https://agentmods.dev/skills/asymptote-labs/agent-beacon/self-verify-beacon-in-sandbox"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/self-verify-beacon-in-sandbox/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/asymptote-labs/agent-beacon/self-verify-beacon-in-sandbox"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/self-verify-beacon-in-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,181 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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: 1 finding, 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 Rogue Agent · line 67
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00114	$0.01181
Opus 5	$0.00057	$0.00590
Sonnet 5	$0.00023	$0.00236
Haiku 4.5	$0.00011	$0.00118

Measured 12d ago against content hash eb64000973f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

self-verify-beacon-in-sandbox 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 12d 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.

.claude/skills/self-verify-beacon-in-sandbox/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Beacon in a sandbox

This repository ships beacon-sandbox, which rents a disposable Linux sandbox from Modal, installs the Beacon under test, runs a real Claude Code session inside it, and checks whether Beacon recorded what the agent did.

Read beacon-sandbox/AGENTS.md for the full operating manual — scenario selection, how to interpret a verdict, and the failure modes that look like Beacon bugs but are not. The commands below are enough to start; that file is what stops you misreading the result.

Step 1: check prerequisites

Always start here. It is free, needs no sandbox, and prints the exact fix for anything missing:

cd beacon-sandbox
go run ./cmd/beacon-sandbox doctor

Add --json for machine-readable output with a top-level ready boolean.

Step 2: resolve what doctor reports

Apply the fix: line it prints, then rerun doctor. The two build artifacts you can resolve yourself:

cd cli/beacon && make build-linux-amd64      # if beacon_binary FAILs
cd beacon-sandbox && go run ./cmd/beacon-sandbox doctor --fix   # downloads the collector

Two prerequisites you must NOT try to resolve yourself:

Modal authentication. modal token new completes through an authenticated web session, so it opens a browser and blocks — running it yourself will hang until timeout. If modal_auth FAILs, ask the user to run it, suggesting they type ! pip install modal && modal token new so the output lands in the conversation. In CI, MODAL_TOKEN_ID and MODAL_TOKEN_SECRET work non-interactively instead.
The Anthropic credential. Never invent, echo, or write a key. If anthropic_credential FAILs, ask the user which of the three paths they want: ANTHROPIC_API_KEY, --api-key-command CMD, or --modal-secret NAME.

Do not proceed to step 3 while doctor reports any FAIL — the run will fail later and more confusingly.

Step 3: run it

go run ./cmd/beacon-sandbox run --scenario s02-bash-command   # one scenario -- do this while iterating
go run ./cmd/beacon-sandbox run                               # the whole suite, ~30 min

Read the full file on GitHub · 95 lines

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.

12d ago First seen · 95 lines · 114 tokens per session scan A eb64000973f9

Subscribe to this mod's changes

self-verify-beacon-in-sandbox is a skill published in the GitHub repository Asymptote-Labs/agent-beacon (436 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 1,181 once invoked, about $0.0006 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.

E2E testing Testing agent-ai-cli agent-security endpoint-security mobile-device-management security-information-and-event-management security-tools

playwright-skill

IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.

Agent-Threat-Rule/agent-threat-rules · 60 tokens

webapp-testing

Toolkit for testing local web applications and browser workflows with MCP browser tools. Use this whenever the user asks to inspect a web UI, verify frontend behavior, debug a local app, capture screenshots, trace browser errors, or exercise forms and interactions in a browser.

Threat-Vector-Security/guardian-agent · 55 tokens

e2e-testing

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

Yaomeng1749/claude-code-digital-nomad-config-pack · 31 tokens

verify

Verify a code change by running the app and checking the user-facing outcome.

m0b1u3/NotitleCode · 15 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

test-warp-ui

Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.

warpdotdev/warp · 55 tokens

agent-beacon: Skill for Claude Code