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.
npx agentmods add skills/gaelic-ghost/socket/prepare-isolated-analysis-labnpx skills add gaelic-ghost/socket --skill prepare-isolated-analysis-labgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/prepare-isolated-analysis-lab)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/prepare-isolated-analysis-lab"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/prepare-isolated-analysis-lab.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00832 |
| Opus 5 | $0.00023 | $0.00416 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
prepare-isolated-analysis-lab 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare Isolated Analysis Lab
Overview
Turn the boundary selected by select-analysis-isolation into a concrete, reviewable control profile before executing untrusted content. Evidence collection and analysis remain owned by their specialist skills.
Read security-lab-control-profile.md before approving a lab.
Workflow
- Consume the approved isolation decision.
- Record authorization, unresolved question, target OS/architecture/privilege, expected behavior, selected boundary, host/guest builds, and VM artifacts that may affect conclusions.
- Select one profile.
- offline static tooling
- monitored Linux dynamic analysis
- monitored macOS dynamic analysis
- network-service research
- nested-virtualization experiment
- Verify a trusted base.
- Record image/restore provenance and digest, guest build, tool versions, clock strategy, resource limits, baseline state or hashes, reset mechanism, and virtualization artifacts that may change observed behavior.
- Remove ambient authority.
- Default host folders/home sharing, clipboard, drag/drop, sockets, SSH agent, browser profiles, cloud credentials, Apple accounts, signing identities, USB, microphone, camera, and unrelated devices to absent.
- Constrain and observe networking.
- Default to offline or simulated services.
- When external connectivity is authorized, record destinations, routes, DNS, monitoring/capture, ingress, egress, and forwarded ports.
- Define a narrow evidence path.
- Name the guest staging location, allowed artifact types, host export directory, hashing and scanning steps, size limits, and owner.
- Run a preflight without executing the target.
- Verify accounts, shares, clipboard, devices, sockets, credentials, network, monitoring, clock, baseline, stop controls, export path, and reset operation.
- Hand the prepared-lab record to
perform-dynamic-malware-analysisor the relevant observation skill. - Verify teardown.
- Stop the workload; export only intended evidence; hash/scan it; revert or remove disposable state; revoke temporary credentials; remove shares/ports/helpers; confirm no workload or integration remains active.
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.
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.
- yesterday First seen · 59 lines · 46 tokens per session scan A 2235ab927cce
prepare-isolated-analysis-lab is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 46 tokens to every session and 832 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
b2-cloud-storage
Manage Backblaze B2 cloud storage. List files, audit usage, estimate cost, clean up stale data, review security posture, and manage lifecycle rules. Use when the user mentions B2, Backblaze, object storage buckets, or storage cleanup.
blob-store
This skill should be used when the user wants a "blob store" or "object storage", names "S3" or an S3-compatible store, needs to "store images / video / files", asks about "multipart upload" or "resumable upload", "signed / presigned URLs", "media storage", "unstructured data at scale", object "versioning", storage…
dns
This skill should be used when the user asks about "DNS", "domain resolution", "GeoDNS / geo routing", "latency-based routing", "weighted / failover routing", "Route 53 / Cloud DNS", an "A/CNAME/ALIAS record", "anycast", or "DNS TTL / propagation". It gives the global front door that maps a name to the right IP and…
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
web-infra-plan
Produce a sprint INFRA.md covering Terraform / gcloud changes — dry-run plan, IAM diff, cost estimate, rollback. Coordinator-only — does not apply infra changes. Pauses for user confirmation. Bias toward GCP+Terraform but works with Pulumi / CloudFormation / Serverless / CDK.
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…