guard

guard is a skill for Claude Code, Codex from prebid/salesagent. It costs 53 tokens per session (662 once invoked), scanned A, original, Apache-2.0.

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.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/prebid/salesagent/guard
Any agent
npx skills add prebid/salesagent --skill guard
Clone the repo
git clone --depth 1 https://github.com/prebid/salesagent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/prebid/salesagent/guard.svg)](https://agentmods.dev/skills/prebid/salesagent/guard)
Your own site
<a href="https://agentmods.dev/skills/prebid/salesagent/guard"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/guard.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00662
Opus 5 $0.00026 $0.00331
Sonnet 5 $0.00011 $0.00132
Haiku 4.5 $0.00005 $0.00066

Measured 2d ago against content hash 23a734fcb44a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/guard/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Read the full file on GitHub · 87 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 87 lines · 53 tokens per session scan A 23a734fcb44a

Subscribe to this mod's changes

guard is a skill published in the GitHub repository prebid/salesagent (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 662 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens