surface-instruction-concern SKILL.md skillA

surface-instruction-concern from jposluns/grc_library is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jposluns/grc_library/surface-instruction-concern@git:20260803.50c809a

Pins git:20260803.50c809a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jposluns/grc_library
Path
guardrails/skills/surface-instruction-concern/SKILL.md
Versions recorded
1
Latest version
git:20260803.50c809a, committed Aug 3, 2026
Size
7,645 bytes
Repository stars
3
License
CC-BY-SA-4.0

Runs the stop-consider-confirm protocol when executing a clear instruction as given would be counterproductive. Use when an instruction would destroy or discard committed work, reduce quality or efficiency with no offsetting benefit, contradict a goal the requestor stated, or rest on an apparently stale belief about current state; and when a brief instruction has both a harmful literal reading and a sensible charitable one. Walks the trigger test, the charitable-interpretation and stale-state…

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

# Surface Instruction Concern (before executing it)

## Overview

The failure mode this skill interrupts: fast, compliant execution of an
instruction that is perfectly clear and still the wrong thing to do, because its
execution as given would cost the requestor something they did not foresee. The
highest-severity shape is the silent most-destructive-literal reading: a brief
instruction ("wind down after this") taken to authorize destroying committed work
the requestor did not know existed. The requestor's actual interest, not
compliance, is the goal; a one-sentence confirmation is cheap, and unwinding
executed damage is not.

The canonical rule
([`surface-counterproductive-instructions`](../../governance/surface-counterproductive-instructions.md))
defines the five trigger classes and the calibration; this skill is its workflow
wrapper for the moment an instruction lands and something about executing it as
given feels net-negative.

## When to Use

- Executing the instruction as given would REDUCE efficiency, effectiveness, or
  productivity, with no offsetting benefit the requestor named.
- Executing it as given would lower quality or correctness (introduce a defect,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jposluns/grc_library/surface-instruction-concern@sha256:002b989330e88922

The line at the top of this page pins the label git:20260803.50c809a, 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_r4ns37xjimswhqnp.svg)](https://markdownregistry.com/a/art_r4ns37xjimswhqnp)

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

Versions

The registry has recorded 1 version of this file, committed on Aug 3, 2026.

versioncommittedcommitsizeaudit
git:20260803.50c809a latest2026-08-03 50c809a 7,645 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 (7645 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

jposluns/grc_library · 3 stars · license CC-BY-SA-4.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_r4ns37xjimswhqnp
GET https://markdownregistry.com/api/v1/resolve?ref=jposluns/grc_library/surface-instruction-concern
GET https://markdownregistry.com/api/v1/blob/002b989330e88922227724baf7abe54f20cedbea5c90490e7416aa289bf969bf

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 jposluns/grc_library

CLAUDE.md@.claude CLAUDE.md file
jposluns/grc_library · .claude/CLAUDE.md
git:20261105.e4e9c35 · audit A · 3 stars
addyosmani-ci-cd-and-automation SKILL.md skill
jposluns/grc_library · .claude/skills/addyosmani-ci-cd-and-automation/SKILL.md · Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to…
git:20261002.8fbb737 · audit A · 3 stars
addyosmani-code-review-and-quality SKILL.md skill
jposluns/grc_library · .claude/skills/addyosmani-code-review-and-quality/SKILL.md · Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another…
git:20261002.8fbb737 · audit A · 3 stars
addyosmani-context-engineering SKILL.md skill
jposluns/grc_library · .claude/skills/addyosmani-context-engineering/SKILL.md · Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching…
git:20261002.8fbb737 · audit A · 3 stars
addyosmani-security-and-hardening SKILL.md skill
jposluns/grc_library · .claude/skills/addyosmani-security-and-hardening/SKILL.md · Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external…
git:20261002.8fbb737 · audit A · 3 stars
addyosmani-using-agent-skills SKILL.md skill
jposluns/grc_library · .claude/skills/addyosmani-using-agent-skills/SKILL.md · Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the…
git:20261002.8fbb737 · audit A · 3 stars
ci-wait SKILL.md skill
jposluns/grc_library · .claude/skills/ci-wait/SKILL.md · Discipline for waiting on PR CI, a GitHub subscription, or any background task in grc_library. Use whenever a wait is…
git:20261002.9985b75 · audit A · 3 stars
clean-language SKILL.md skill
jposluns/grc_library · .claude/skills/clean-language/SKILL.md · Draft, rewrite, edit, review, or quality-assure prose using the Clean Language standard. Use for emails, Teams or…
git:20260801.d8bb037 · audit A · 3 stars
corpus-management SKILL.md skill
jposluns/grc_library · .claude/skills/corpus-management/SKILL.md · Corpus-Management umbrella skill for grc_library. Use when creating, editing, reviewing or auditing corpus documents or…
git:20261026.1c2fa83 · audit A · 3 stars
pr-close-out SKILL.md skill
jposluns/grc_library · .claude/skills/pr-close-out/SKILL.md · Run the full PR lifecycle and session-migration procedure for grc_library. Load before authoring any change (including…
git:20261016.ff50378 · audit A · 3 stars
corpus-management SKILL.md skill
jposluns/grc_library · .corpus-management/core/skill/SKILL.md · Corpus-Management umbrella skill for grc_library. Use when creating, editing, reviewing or auditing corpus documents or…
git:20261026.1c2fa83 · audit A · 3 stars
CLAUDE.md@guardrails CLAUDE.md file
jposluns/grc_library · guardrails/CLAUDE.md
git:20261027.22a8e2c · audit A · 3 stars

Every file in jposluns/grc_library

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