guard SKILL.md skillA

guard from jun0-ds/sonmat is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jun0-ds/sonmat/guard@git:20260928.900ac85

Pins git:20260928.900ac85 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jun0-ds/sonmat
Path
skills/guard/SKILL.md
Versions recorded
5
Latest version
git:20260928.900ac85, committed Sep 28, 2026
First version recorded
Apr 2, 2026
Size
5,508 bytes
Repository stars
5
License
BSD-3-Clause

Main-side verification checks — pre-commit test / sensitive-file blocking, discipline conformance, novel-trap detection. Pure verify-and-flag; persistence of findings is scribe's job, intent-artifact match is witness's.

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

# Guard — Main-Side Verification Checks

Automatic verification layer running in the main session (System 1). No agent spawn.

Guard covers **verification** checks that main can reliably do on itself: sensitive files, test execution, discipline conformance, and detection of novel traps during work. Guard is pure verify-and-flag — it detects, it warns, it blocks. It does **not** record, accumulate, or persist findings; those belong to scribe (post-work persistence). It also does **not** verify whether the artifact matches the user's intent; that check is structurally unreliable when done inside the agent that produced the artifact, and is delegated to [witness](../../agents/sonmat-witness.md).

**Scope boundaries**:

| Check kind | Owner | Why |
|---|---|---|
| Test execution, sensitive file blocking, discipline conformance, novel-trap detection | **guard** | Real-time verification during work; synchronous check-and-block at decision points |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jun0-ds/sonmat/guard@sha256:a8f06b7a6f147e63

The line at the top of this page pins the label git:20260928.900ac85, 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_ytdwlagnjmpjjvpf.svg)](https://markdownregistry.com/a/art_ytdwlagnjmpjjvpf)

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

Versions

The registry has recorded 5 versions of this file, between Apr 2, 2026 and Sep 28, 2026, about one every 45 days.

versioncommittedcommitsizeaudit
git:20260928.900ac85 latest2026-09-28 900ac85 5,508 BA view · diff
git:20260828.212f32c2026-08-28 212f32c 5,508 BA view · diff
git:20260414.1f06a652026-04-14 1f06a65 5,507 BA view · diff
git:20260414.1ac12c32026-04-14 1ac12c3 5,430 BA view · diff
git:20260402.4491b6f2026-04-02 4491b6f 4,878 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 (5508 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

jun0-ds/sonmat · 5 stars · license BSD-3-Clause · pushed 2026-10-12 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ytdwlagnjmpjjvpf
GET https://markdownregistry.com/api/v1/resolve?ref=jun0-ds/sonmat/guard
GET https://markdownregistry.com/api/v1/blob/a8f06b7a6f147e63c0898bf3a64b9beef778ec8ecb4edc48cf3c95816729a49f

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 jun0-ds/sonmat

autoloop SKILL.md skill
jun0-ds/sonmat · skills/autoloop/SKILL.md · 범용 자율 루프 — 기획→정의→실행→평가→판단→기록→반복. 에스컬레이션 판단 포함.
git:20261012.4fe924e · audit A · 5 stars
devil SKILL.md skill
jun0-ds/sonmat · skills/devil/SKILL.md · 요청된 계획·해석·판단에서 목적 달성을 좌우하는 가정을 검토하고 다음 선택에 도움이 되는 반론을 제시한다.
git:20261003.89c6510 · audit A · 5 stars
inspect SKILL.md skill
jun0-ds/sonmat · skills/inspect/SKILL.md · Trigger-reactive discovery-led depth — when a System 1 signal surfaces (blast radius, shared code, infra, auth…
git:20260414.1ac12c3 · audit A · 5 stars
punch SKILL.md skill
jun0-ds/sonmat · skills/punch/SKILL.md · Punch list — completeness and residue check before delivery. Finds what's missing that should exist (omission) and…
git:20260522.161955d · audit A · 5 stars
scribe SKILL.md skill
jun0-ds/sonmat · skills/scribe/SKILL.md · Post-work persistence layer — observes completed work and writes what should outlive the session. Bridge notes…
git:20261012.4fe924e · audit A · 5 stars

Every file in jun0-ds/sonmat

Other files named guard

guard SKILL.md skill
garrytan/gstack · guard/SKILL.md · Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
v0.1.0 · audit A · 140,694 stars
guard SKILL.md skill
autonomous-ai/lampos · skills/guard/SKILL.md · Guard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house"…
git:20260911.2ff98c0 · audit B · 548 stars
guard SKILL.md skill
autonomous-ai/autonomous-os · skills/guard/SKILL.md · Guard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house"…
git:20260911.2ff98c0 · audit B · 548 stars
guard SKILL.md skill
autonomous-ai/physical-ai-operating-system · skills/guard/SKILL.md · Guard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house"…
git:20260911.2ff98c0 · audit B · 548 stars
guard SKILL.md skill
tonydzi/second-brain-starter-kit · skills/guard/SKILL.md · Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
v0.1.0 · audit A · 14 stars
guard SKILL.md skill
tonydzi/second-brain-starter-kit · skills/gstack/guard/SKILL.md · Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
v0.1.0 · audit A · 14 stars
guard SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/gstack/.agents/skills/gstack-guard/SKILL.md · Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP…
git:20260328.17430b8 · audit A · 12 stars
guard SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/gstack/guard/SKILL.md · Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP…
v0.1.0 · audit A · 12 stars

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