harness-audit SKILL.md skillA

harness-audit from undefined-ui/second-brain-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add undefined-ui/second-brain-os/harness-audit@git:20261007.c7fa35b

Pins git:20261007.c7fa35b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
undefined-ui/second-brain-os
Path
plugins/agents-course/skills/harness-audit/SKILL.md
Versions recorded
2
Latest version
git:20261007.c7fa35b, committed Oct 7, 2026
First version recorded
Sep 29, 2026
Size
3,444 bytes
Repository stars
1,109
License
MIT

Audit an agent's harness against the four rings: containment, guides, sensors, permissions. Use when the user asks whether their agent setup is safe, wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails, or asks what a bad session could break. Read-only: reports the blast radius and a hardening list, changes nothing. Do NOT use for context layout (context-audit) or cost routing (gate-check).

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

# Audit the four rings

Theory: [The four rings](https://secondbrainos.dev/#/read/course-4-harness/the-four-rings)
and [Harness practice](https://secondbrainos.dev/#/read/course-4-harness/harness-practice).
Build from the outside in: containment, guides, sensors, permissions. The
order matters because each ring must hold when every ring inside it fails —
a guide can be ignored, a sensor can miss, an approval can be misclicked;
a wall does not care.

## Core rule

Report and rank; never harden anything yourself. The audit's one organising
question is the blast radius: describe the worst session possible under the
current setup and what it costs. If the user asks you to apply fixes
afterwards, that is a normal edit session, not this skill.

## Workflow

1. **Ring one — containment: what can it physically reach?** Where does the
   agent run: the user's checkout or a worktree/container? Which credentials
   are in its environment — a read-only database user or the application's?
   Open internet or an allowlist? Real API keys or test keys? The finding is
   one sentence: "the worst session deletes X and spends Y."
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add undefined-ui/second-brain-os/harness-audit@sha256:44318ce4de3806be

The line at the top of this page pins the label git:20261007.c7fa35b, 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_rzjvzewkdfao2xsa.svg)](https://markdownregistry.com/a/art_rzjvzewkdfao2xsa)

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

Versions

The registry has recorded 2 versions of this file, between Sep 29, 2026 and Oct 7, 2026, about one every 9 days.

versioncommittedcommitsizeaudit
git:20261007.c7fa35b latest2026-10-07 c7fa35b 3,444 BA view · diff
git:20260929.245ba2c2026-09-29 245ba2c 3,474 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 (3444 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

undefined-ui/second-brain-os · 1,109 stars · license MIT · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rzjvzewkdfao2xsa
GET https://markdownregistry.com/api/v1/resolve?ref=undefined-ui/second-brain-os/harness-audit
GET https://markdownregistry.com/api/v1/blob/44318ce4de3806be3b0a27c0a439938c5016e529ac4358796aeb518fc33f3719

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 undefined-ui/second-brain-os

context-audit SKILL.md skill
undefined-ui/second-brain-os · plugins/agents-course/skills/context-audit/SKILL.md · Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to…
git:20261007.c7fa35b · audit A · 1,109 stars
evals-bootstrap SKILL.md skill
undefined-ui/second-brain-os · plugins/agents-course/skills/evals-bootstrap/SKILL.md · Scaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and…
git:20261007.c7fa35b · audit A · 1,109 stars
gate-check SKILL.md skill
undefined-ui/second-brain-os · plugins/agents-course/skills/gate-check/SKILL.md · Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic…
git:20261007.c7fa35b · audit A · 1,109 stars
goal-test SKILL.md skill
undefined-ui/second-brain-os · plugins/agents-course/skills/goal-test/SKILL.md · Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally…
git:20261007.c7fa35b · audit A · 1,109 stars
second-brain-backfill SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-backfill/SKILL.md · Import a large archive into the vault in controlled batches: triage what is worth ingesting, process oldest first…
git:20260908.1615b29 · audit A · 1,109 stars
second-brain-changed-my-mind SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-changed-my-mind/SKILL.md · Trace where the user's recorded position on something has shifted: superseded claims, contradictions between sources of…
git:20260908.1615b29 · audit A · 1,109 stars
second-brain-chat-import SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-chat-import/SKILL.md · Triage an exported chat history into what to ingest, what to archive and what to delete, with a privacy pass first. Use…
git:20260908.1615b29 · audit A · 1,109 stars
second-brain-graph SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-graph/SKILL.md · Analyse the vault's link graph and report on its shape: orphan rate, average degree, components, hubs, bridges and…
git:20260908.1615b29 · audit A · 1,109 stars
second-brain-ingest SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-ingest/SKILL.md · Turn raw source material in a second-brain vault into linked wiki pages: read the source, split it into concepts and…
git:20260907.8c47c65 · audit A · 1,109 stars
second-brain-lint SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-lint/SKILL.md · Audit a second-brain vault for structural problems and repair them: broken wikilinks, orphan pages, empty stubs…
git:20260907.8c47c65 · audit A · 1,109 stars
second-brain-merge SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-merge/SKILL.md · Merge two pages that describe the same thing, preserving every distinct claim, redirecting inbound links, and recording…
git:20260908.1615b29 · audit A · 1,109 stars
second-brain-metrics SKILL.md skill
undefined-ui/second-brain-os · skills/second-brain-metrics/SKILL.md · Record a dated snapshot of the vault's health numbers and compare against previous snapshots so trends are visible. Use…
git:20260908.1615b29 · audit A · 1,109 stars

Every file in undefined-ui/second-brain-os

Other files named harness-audit

harness-audit SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/harness-audit/SKILL.md · Harness 能力面审计(7 维度评分 + 改进建议)。对角色覆盖、技能完整性、Hook 有效性、规则执行、命令覆盖、文档质量、集成深度进行全面评估,输出 Overall Score、Dimension Scores 和 Top…
git:20260512.6523792 · audit A · 1,352 stars
harness-audit SKILL.md skill
kanevry/session-orchestrator · .codex-plugin/skills/harness-audit/SKILL.md · Run the harness audit and report the rubric score for this repository
git:20260916.3ebf0e9 · audit A · 53 stars
harness-audit SKILL.md skill
kanevry/session-orchestrator · .cursor/skills/harness-audit/SKILL.md · Run the harness audit and report the rubric score for this repository
git:20260916.dd05e0f · audit A · 53 stars
harness-audit SKILL.md skill
kanevry/session-orchestrator · .agents/skills/harness-audit/SKILL.md · Run the harness audit and report the rubric score for this repository
git:20260919.176b605 · audit A · 53 stars
harness-audit SKILL.md skill
kanevry/session-orchestrator · skills/harness-audit/SKILL.md · Run the harness audit and report the rubric score for this repository
git:20260916.3ebf0e9 · audit A · 53 stars
harness-audit SKILL.md skill
fmslutions/harness-audit · skills/harness-audit/SKILL.md · Audits and restructures a project's AI agent harness (CLAUDE.md, AGENTS.md, GEMINI.md, rules, skills, hooks, docs and…
v1.5.2 · audit A · 7 stars

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