agent-soak-testing SKILL.md skillA

agent-soak-testing from stancsz/northstar is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add stancsz/northstar/agent-soak-testing@git:20261030.2e11764

Pins git:20261030.2e11764 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
stancsz/northstar
Path
skills/agent-soak-testing/SKILL.md
Versions recorded
1
Latest version
git:20261030.2e11764, committed Oct 30, 2026
Size
1,997 bytes
Repository stars
3
License
MIT

Plan, run, and evaluate bounded repeated-use reliability and instruction-drift soak tests for agent harnesses and models.

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

# Agent Soak Testing

Use this skill when evaluating whether an AI agent harness, skill stack, or model stays reliable and resists instruction drift under repeated use over time. The [Soak framework](https://github.com/stancsz/soak) is a separate external runner; this skill provides evaluation guidance and does not install the runner or imply that a live target has been exercised.

1. **Define target and budget bounds first:** Name the exact agent harness, model, workload, environment, and pass/fail invariant. Lock authorized duration, request rate, concurrency, and spend ceiling before calling any paid or shared service. Never present synthetic or mock runs as real-system evidence.
2. **Design deterministic, sanitized cases:** Give each case a stable unique ID and explicit observable assertions (including tool use, state continuity, or multi-turn steering only when relevant). Strip secrets and sensitive data from all inputs and captured outputs.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ev3pl3tlumhmwojv/fd3b752920b12672f20bb3af9a930b0595cf313ba0e4e7d0b85d316497fc74dc.json

Then /plugin install agent-soak-testing@markdownregistry-ev3pl3tlumhmwojv in Claude Code. It installs git:20261030.2e11764, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add stancsz/northstar/agent-soak-testing@sha256:fd3b752920b12672

The line at the top of this page pins the label git:20261030.2e11764, 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_ev3pl3tlumhmwojv.svg)](https://markdownregistry.com/a/art_ev3pl3tlumhmwojv)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in stancsz/northstar/agent-soak-testing since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of agent-soak-testing from somewhere else? Ask it: where did my agent-soak-testing come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Oct 30, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261030.2e11764 latest2026-10-30 2e11764 1,997 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (1997 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

stancsz/northstar · 3 stars · license MIT · pushed 2026-11-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ev3pl3tlumhmwojv
GET https://markdownregistry.com/api/v1/resolve?ref=stancsz/northstar/agent-soak-testing
GET https://markdownregistry.com/api/v1/blob/fd3b752920b12672f20bb3af9a930b0595cf313ba0e4e7d0b85d316497fc74dc

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 stancsz/northstar

AGENTS.md AGENTS.md file
stancsz/northstar · AGENTS.md
git:20261114.67473cc · audit A · 3 stars
advisor-council SKILL.md skill
stancsz/northstar · skills/advisor-council/SKILL.md · Consult an independent advisor or complexity-based council for capability risks, hard blockers, unresolved…
git:20261114.b07701e · audit A · 3 stars
independent-qa SKILL.md skill
stancsz/northstar · skills/independent-qa/SKILL.md · Nonauthor functional, visual, runtime, adversarial, and spec acceptance review; verify material repairs against exact…
git:20261030.2e11764 · audit A · 3 stars
northstar SKILL.md skill
stancsz/northstar · skills/northstar/SKILL.md · Deliver verified outcomes with zero silent drift. Central workflow for intent locking, multi-agent orchestration…
git:20261114.67473cc · audit A · 3 stars
subagent-orchestration SKILL.md skill
stancsz/northstar · skills/subagent-orchestration/SKILL.md · Orchestrate bounded multi-agent work across native subagents, Codex CLI, and Claude Code CLI; manage role hierarchy…
git:20261114.67473cc · audit A · 3 stars
task-completion-review SKILL.md skill
stancsz/northstar · skills/task-completion-review/SKILL.md · Audit proposed stops, completions, waits, or escalations against original requirements and evidence; includes opt-in…
git:20261114.59e3648 · audit A · 3 stars
windows-app-watchdog SKILL.md skill
stancsz/northstar · skills/windows-app-watchdog/SKILL.md · Monitor a selected Windows desktop GUI app via a per-user Scheduled Task and relaunch it when its top-level window…
git:20261030.2e11764 · audit A · 3 stars

Every file in stancsz/northstar

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