Skip to content
Agentmart
Submit a tool

architecture-guardrails

Keep long-running work inside agreed boundaries by tracking scope drift, upgrade conditions, and design decisions before implementation silently expands.

Skill by gclm

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/gclm-architecture-guardrails

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Keep long-running work inside agreed boundaries by tracking scope drift, upgrade conditions, and design decisions before implementation silently expands.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/architecture-guardrails

What's inside

Skill name
architecture-guardrails
Description
Keep long-running work inside agreed boundaries by tracking scope drift, upgrade conditions, and design decisions before implementation silently expands.
License
MIT
Instructions
24 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • human-escalation-gates.md · references/
  • scope-drift-signals.md · references/

SKILL.md (first lines)

# Architecture Guardrails

Use when a task is at risk of drifting across architecture, migration, API, or service-boundary lines.

## Read First

- `skills/harness/architecture-guardrails/references/scope-drift-signals.md`
- `skills/harness/architecture-guardrails/references/human-escalation-gates.md`
- `docs/architecture/decisions/runtime-promotion-gates.md`

## Goals

- keep scope and non-goals explicit
- detect when execution should step back to `plan`
- record decisions before the task silently changes shape

## Process

1. restate the current scope and non-goals
2. look for scope-drift signals
3. decide whether the task can continue in `build`
4. escalate to `plan`, proposal, ADR, or review when needed

From gclm/super-stack, MIT.

More from gclm/super-stack

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 29, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from gclm

Cite this page

architecture-guardrails skill. Agent Mart. https://agentmart.dev/skills/gclm-architecture-guardrails (last updated 2026-10-24)