design-integrity-review

design-integrity-review is a skill for Claude Code, Codex from a1024053774/design-integrity-guardrails. It costs 58 tokens per session (1,012 once invoked), scanned A, original, MIT.

A read-only skill that routes a completed change through a focused structural-integrity review or an independent behavioral-acceptance review. It checks a frozen candidate at a completion checkpoint.

In plain words
What is it for?
It is for reviewing repository changes after implementation, checking architecture-gate status, and identifying scope, design, or evidence problems without editing files.
Why use it?
It helps find structural shortcuts and sends changes involving tests or other acceptance evidence to the appropriate review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing repository changes after implementation, checking architecture-gate status, and identifying scope, design, or evidence problems without editing files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a1024053774/design-integrity-guardrails/design-integrity-review
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.

Any agent
npx skills add a1024053774/design-integrity-guardrails --skill design-integrity-review
Clone the repo
git clone --depth 1 https://github.com/a1024053774/design-integrity-guardrails

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 design-integrity-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/design-integrity-review/github.svg)](https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/design-integrity-review)
Your own site
<a href="https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/design-integrity-review"><img src="https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/design-integrity-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-integrity-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/design-integrity-review"><img src="https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/design-integrity-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,012 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00058 $0.01012
Opus 5 $0.00029 $0.00506
Sonnet 5 $0.00012 $0.00202
Haiku 4.5 $0.00006 $0.00101

Measured 5d ago against content hash 21c6e0f6894d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

design-integrity-review 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 5d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/design_integrity.py, scripts/integrity_hook.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

design-integrity-review/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Integrity Review

Review one candidate change at a completion checkpoint. This skill is a router and a focused structural review, not a general QA pass. It is read-only: do not edit files, tests, fixtures, commits, branches, deployments, or external systems.

Relationship with reality-first-engineering

reality-first-engineering is the earlier architecture gate. If the task has incomplete requirements, domain rules, external behavior, acceptance criteria, or other unverified facts that could change the architecture, confirm that a REALITY GATE: PASS exists for the current architecture epoch before spending review budget here. If it does not, stop this route and send the agent to the reality gate; do not use a structural review to rationalize an unverified design. A new measurement that invalidates the architecture starts a new reality epoch and invalidates the candidate for this review.

The reality gate and this review have different jobs: the former tests whether the direction is justified; this skill checks whether the frozen implementation introduced structural or acceptance shortcuts. Neither creates a second project ledger or repeats the other review.

Choose one route

Inspect the task, active instructions, the candidate diff, and changed paths first.

  • If the change touches autoresearch, eval, benchmark, harness, grader, golden, oracle, or another explicit evaluation surface, invoke the behavioral-acceptance-review skill and delegate exactly one review to the configured acceptance-auditor.
  • Otherwise, review only structural risks introduced by the candidate: broad or swallowed exception handling, fallback/retry paths, compatibility branches, duplicate or parallel APIs, and local patches that bypass root-cause ownership.
  • If both kinds of risk are present, use one acceptance-auditor call and include the scanner's structural markers as review context. Do not start a second reviewer.
  • Routine unit-test edits, generated files that are not an acceptance surface, documentation-only, formatting-only, screenshot-only, and fixture maintenance changes do not require this skill unless the task explicitly requests review.

Read the full file on GitHub · 88 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago Changed · +2 lines · -9 tokens per session 21c6e0f6894d
  2. 11d ago First seen · 86 lines · 67 tokens per session scan A 32d04eb57330

Subscribe to this mod's changes

design-integrity-review is a skill published in the GitHub repository a1024053774/design-integrity-guardrails (0 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,012 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 2026-08-31.

Related

Other skills, from other repositories