How do I install the Guard skill?

Run npx skillmds@latest add prebid/guard in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Guard safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Guard?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Guard free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

prebid (@prebid) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Guard by prebid — Agent Skill

Name: Guard
Author: prebid

Guard

Create structural guard tests that enforce architecture principles on every `make quality` run. Guards are AST-scanning tests that prevent categories of violations automatically. Available guards: schema-inheritance, boundary-completeness, query-type-safety, no-error-dicts.

prebid 088b410 2.6 KB Updated Sep 17, 2026

File contents

Structural Guard Creation

Create AST-scanning enforcement tests that catch architecture violations automatically. Each guard runs on make quality and prevents regressions.

Args

/guard <guard-name-1> [guard-name-2] ...

Guard names (space-separated). Each gets a test file at tests/unit/test_architecture_{guard_name}.py.

Available Guards

Guard	What It Enforces
schema-inheritance	Schema classes extend correct adcp library base types
boundary-completeness	MCP/A2A/REST wrappers expose all _impl parameters
query-type-safety	DB queries use column types matching the column definition
no-error-dicts	_impl functions raise exceptions, never return error dicts

Custom guard names are also supported — the research atom will determine what to enforce based on the name and #1050/#1066 principles.

Existing Structural Guards

These already exist (don't recreate):

test_no_toolerror_in_impl.py — No ToolError in _impl functions
test_transport_agnostic_impl.py — No transport imports in _impl
test_impl_resolved_identity.py — _impl accepts ResolvedIdentity

Protocol

Step 1: Cook the molecule

python3 .claude/scripts/cook_formula.py \
  --formula .claude/formulas/structural-guard.yaml \
  --var "GUARD_NAMES={all_args}" \
  --epic-title "Guards: {all_args}"

Dry run first (recommended):

python3 .claude/scripts/cook_formula.py \
  --formula .claude/formulas/structural-guard.yaml \
  --var "GUARD_NAMES={all_args}" \
  --epic-title "Guards: {all_args}" \
  --dry-run

Step 2: Walk the molecule

bd ready → bd show <atom-id> → execute → bd close <atom-id> → repeat

Each guard goes through: research → scan → write-guard → mark-known → verify → commit.

Step 3: Done when all atoms closed

All guards committed and passing in make quality.

Key Principles

Allowlists shrink, never grow. New violations fail the guard immediately.
FIXME comments link to beads tasks. Every known violation has a tracker.
Guards follow existing patterns. Read the 3 existing structural tests first.

---name: guarddescription: Create structural guard tests that enforce architecture principles on every `make quality` run. Guards are AST-scanning tests that prevent categories of violations automatically. Available guards: schema-inheritance, boundary-completeness, query-type-safety, no-error-dicts.---# Structural Guard CreationCreate AST-scanning enforcement tests that catch architecture violationsautomatically. Each guard runs on `make quality` and prevents regressions.## Args```/guard <guard-name-1> [guard-name-2] ...```Guard names (space-separated). Each gets a test file at`tests/unit/test_architecture_{guard_name}.py`.## Available Guards| Guard | What It Enforces ||-------|-----------------|| schema-inheritance | Schema classes extend correct adcp library base types || boundary-completeness | MCP/A2A/REST wrappers expose all _impl parameters || query-type-safety | DB queries use column types matching the column definition || no-error-dicts | _impl functions raise exceptions, never return error dicts |Custom guard names are also supported — the research atom will determinewhat to enforce based on the name and #1050/#1066 principles.## Existing Structural GuardsThese already exist (don't recreate):- `test_no_toolerror_in_impl.py` — No ToolError in _impl functions- `test_transport_agnostic_impl.py` — No transport imports in _impl- `test_impl_resolved_identity.py` — _impl accepts ResolvedIdentity## Protocol### Step 1: Cook the molecule```bashpython3 .claude/scripts/cook_formula.py \ --formula .claude/formulas/structural-guard.yaml \ --var "GUARD_NAMES={all_args}" \ --epic-title "Guards: {all_args}"```**Dry run first** (recommended):```bashpython3 .claude/scripts/cook_formula.py \ --formula .claude/formulas/structural-guard.yaml \ --var "GUARD_NAMES={all_args}" \ --epic-title "Guards: {all_args}" \ --dry-run```### Step 2: Walk the molecule```bd ready → bd show <atom-id> → execute → bd close <atom-id> → repeat```Each guard goes through: research → scan → write-guard → mark-known → verify → commit.### Step 3: Done when all atoms closedAll guards committed and passing in `make quality`.## Key Principles- **Allowlists shrink, never grow.** New violations fail the guard immediately.- **FIXME comments link to beads tasks.** Every known violation has a tracker.- **Guards follow existing patterns.** Read the 3 existing structural tests first.## See Also- `/surface` — Create entity test suites (what the guards protect)- `/remediate` — Fill entity test stubs (fix the violations guards find)- `/mol-execute` — Execute individual beads tasks

Frequently asked questions