A verification procedure for Dormice, a daemon with public HTTP and E2B interfaces. It builds the project, starts an isolated fake runtime, and tests the service through its supported network routes.

Use it to verify Dormice health checks, HTTP and E2B interactions, streaming request formats, error handling, and resource cleanup. It does not establish Docker or gVisor behavior when using the fake executor.

It checks whether the claimed runtime flow actually works, including authentication, streaming responses, malformed requests, replay or concurrency behavior, and cleanup. It also separates facts that need a real Linux host from those the fake runtime can test.

How BitMiracle-AI/Dormice configures Claude Code and Codex

About the project

Dormice is a self-hosted platform that gives AI agents persistent, isolated environments for running code and managing files on one machine. It is for keeping agent sandboxes available across sessions while automatically moving idle environments through lower-resource states and restoring them when needed. The catalogue contains two skills for working with Dormice.

BitMiracle-AI/Dormice · 1,709 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to BitMiracle-AI/Dormice. 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/BitMiracle-AI/Dormice/main/.agents/skills/verify/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/BitMiracle-AI/Dormice

Made for: Claude Code, Codex.

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/bitmiracle-ai/dormice/verify/github.svg)](https://agentmods.dev/skills/bitmiracle-ai/dormice/verify)

Your own site

<a href="https://agentmods.dev/skills/bitmiracle-ai/dormice/verify"><img src="https://agentmods.dev/badge/skills/bitmiracle-ai/dormice/verify/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/bitmiracle-ai/dormice/verify"><img src="https://agentmods.dev/badge/skills/bitmiracle-ai/dormice/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 270 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 pass 7 Sept 2026

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	$0.00001	$0.00270
Opus 5.5	$0.00000	$0.00108
Sonnet 5.5	$0.00000	$0.00054
Haiku 4.5	$0.00000	$0.00027

Measured 2mo ago against content hash 988cb11aaab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify 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.

.agents/skills/verify/SKILL.md · 14 lines

What it actually says

Verify Dormice runtime behavior

Run pnpm build before verification; the black-box surface is packages/server/dist/main.js.
Launch an isolated fake daemon with an unused port, a temporary absolute DORMICE_DB_PATH/DORMICE_DATA_DIR, a 64-hex DORMICE_API_TOKEN, and DORMICE_EXECUTOR=fake.
Wait for GET /healthz, then drive native or E2B routes only over HTTP. E2B control auth is X-API-KEY: e2b_<token>; envd requests use the returned sandboxID/envdAccessToken as E2b-Sandbox-Id and X-Access-Token.
Connect streaming requests use one envelope: flag byte 0, four-byte big-endian JSON length, then JSON bytes. Parse responses as repeated envelopes.
Capture response status/body inline. Probe malformed input, replay/concurrency, and resource cleanup around the claimed flow.
Stop the daemon and remove its temporary directory. Docker/gVisor process facts require the Linux test host and cannot be established with the fake executor.

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.

2mo ago First seen · 14 lines · 1 tokens per session scan A 988cb11aaab4

Subscribe to this mod's changes

verify is a skill published in the GitHub repository BitMiracle-AI/Dormice (1,709 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1 tokens to every session and 270 once invoked, about $0.0000 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.

Testing agents ai-agents code-execution docker e2b gvisor

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

skill-release-gate

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

rohitg00/ai-engineering-from-scratch · 36 tokens

verify-omnigent

Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…

omnigent-ai/omnigent · 100 tokens

adk-go-self-review

Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…

google/adk-go · 87 tokens

python-sdk

Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.

ComposioHQ/composio · 60 tokens

Dormice: Skill for Claude Code