host-test SKILL.md skillA

host-test from scriptedalchemy/agent-bundle is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add scriptedalchemy/agent-bundle/host-test@git:20260915.7bdc8f8

Pins git:20260915.7bdc8f8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
scriptedalchemy/agent-bundle
Path
examples/host-test/src/skills/host-test/SKILL.md
Versions recorded
3
Latest version
git:20260915.7bdc8f8, committed Sep 15, 2026
First version recorded
Sep 3, 2026
Size
1,474 bytes
Repository stars
12
License
Apache-2.0

Inspect host-test capture logs for hooks, MCP, conversation, session, or lineage. Use when debugging what a host sent this probe.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Host test probe

This plugin records every hook event the host dispatches to it, plus every
call to its own MCP servers, into one NDJSON log and a durable state summary.
Nothing it records is sent anywhere; the log stays on this machine.

## Inspect or probe

For a log or identity question, call the `host-test` MCP server's `dump` tool
and report the relevant observed ids and log path. Existing records may answer
the question without a live probe. The `dump` call itself is recorded;
distinguish absent evidence from an unsupported host capability.

For a requested live probe, generate only the evidence needed:

- Run a harmless shell command such as `pwd` for tool-hook evidence.
- Create a small scratch file for file-edit-hook evidence.
- If `host-test-raw` exposes `probe`, call it with your role (`root` or
  `subagent`) as the note.
- For parent/subagent lineage, ask a subagent to run the shell and available
  probe calls, then dump the resulting records. A log-only request does not
  require spawning an agent.

Dump the resulting records and report the relevant ids verbatim, without
editing the log. Do not include unrelated payloads in the response.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add scriptedalchemy/agent-bundle/host-test@sha256:1c2157429ac84c53

The line at the top of this page pins the label git:20260915.7bdc8f8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_eosfes2nscilvoim.svg)](https://markdownregistry.com/a/art_eosfes2nscilvoim)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Sep 3, 2026 and Sep 15, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20260915.7bdc8f8 latest2026-09-15 7bdc8f8 1,474 BA view · diff
git:20260908.2b7f8212026-09-08 2b7f821 1,438 BA view · diff
git:20260903.21af4ce2026-09-03 21af4ce 1,464 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1474 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

scriptedalchemy/agent-bundle · 12 stars · license Apache-2.0 · pushed 2026-10-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_eosfes2nscilvoim
GET https://markdownregistry.com/api/v1/resolve?ref=scriptedalchemy/agent-bundle/host-test
GET https://markdownregistry.com/api/v1/blob/1c2157429ac84c5328b82e775b6ae96a25c986015283f58d6602c5ed64624e7b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from scriptedalchemy/agent-bundle

AGENTS.md AGENTS.md file
scriptedalchemy/agent-bundle · AGENTS.md
git:20260908.fd20425 · audit A · 12 stars
CLAUDE.md CLAUDE.md file
scriptedalchemy/agent-bundle · CLAUDE.md
git:20260908.fd20425 · audit B · 12 stars
curate-audiobooks SKILL.md skill
scriptedalchemy/agent-bundle · examples/audiobook-curator/src/skills/curate-audiobooks/SKILL.md · Inventory, match, convert, repair, or audit audiobooks. Use for a concrete curation step, not general media discussion.
git:20260925.96b2519 · audit A · 12 stars
service-readiness SKILL.md skill
scriptedalchemy/agent-bundle · examples/mcp-app/src/skills/service-readiness/SKILL.md · Assess service health evidence for a release, incident, or handoff. Use when a readiness verdict is requested.
git:20260915.7bdc8f8 · audit A · 12 stars
dependency-upgrade SKILL.md skill
scriptedalchemy/agent-bundle · examples/skills-starter/src/skills/dependency-upgrade/SKILL.md · Plan, implement, or review a dependency upgrade that may change APIs or runtime. Use when bumping or replacing a…
git:20260915.7bdc8f8 · audit A · 12 stars
incident-triage SKILL.md skill
scriptedalchemy/agent-bundle · examples/skills-starter/src/skills/incident-triage/SKILL.md · Triage a suspected active production incident with evidence for containment and handoff.
git:20260915.7bdc8f8 · audit A · 12 stars
release-review SKILL.md skill
scriptedalchemy/agent-bundle · examples/skills-starter/src/skills/release-review/SKILL.md · Review a release candidate and issue an evidence-based go/no-go verdict.
git:20260908.2b7f821 · audit A · 12 stars
agent-bundle-native-smoke SKILL.md skill
scriptedalchemy/agent-bundle · fixtures/contracts/hosts/claude/candidate/skills/agent-bundle-native-smoke/SKILL.md · Reply with the bounded smoke marker when explicitly requested.
git:20260814.8a052c0 · audit A · 12 stars
agent-bundle-codex-smoke SKILL.md skill
scriptedalchemy/agent-bundle · fixtures/contracts/hosts/codex/candidate/skills/agent-bundle-codex-smoke/SKILL.md · Bounded native-contract smoke Skill.
git:20260819.5594464 · audit A · 12 stars
review SKILL.md skill
scriptedalchemy/agent-bundle · fixtures/integration/comprehensive/src/skills/review/SKILL.md · Reviews the integration fixture.
git:20260902.9514cec · audit B · 12 stars
triage SKILL.md skill
scriptedalchemy/agent-bundle · fixtures/integration/micro-eval/src/skills/triage/SKILL.md · Reports the highest-risk regression recorded in a repository fixture.
git:20260902.9514cec · audit A · 12 stars
review SKILL.md skill
scriptedalchemy/agent-bundle · fixtures/integration/packed-release/src/skills/review/SKILL.md · Reviews the packed release fixture.
git:20260902.9514cec · audit B · 12 stars

Every file in scriptedalchemy/agent-bundle

Browse by kind, by grade A, or by owner.