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.
npx skills add a1024053774/design-integrity-guardrails --skill design-integrity-reviewgit clone --depth 1 https://github.com/a1024053774/design-integrity-guardrailsWrote 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.
[](https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/design-integrity-review)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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 thebehavioral-acceptance-reviewskill and delegate exactly one review to the configuredacceptance-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-auditorcall 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.
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.
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.
- 5d ago Changed · +2 lines · -9 tokens per session 21c6e0f6894d
- 11d ago First seen · 86 lines · 67 tokens per session scan A 32d04eb57330
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.
Other skills, from other repositories
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
gentle-ai
Use Gentle AI harness discipline for Pi work: clarify first, preserve OpenSpec artifacts, use strict TDD where available, delegate through subagents when useful, and protect review workload.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
qa
Use to verify that code works correctly — browser-based testing with Playwright, native app testing with computer use, CLI testing, API testing, or root-cause debugging. Supports --quick, --standard, --thorough modes. Triggers on /qa.
ring:adding-multi-tenancy
Adding database-per-tenant isolation into a Go service end-to-end via an 11-gate cycle: detects the stack, audits compliance, then dispatches backend agents to implement tenantId-from-JWT routing through the lib-commons v5 dispatch layer (config, middleware, repositories, metrics, tests) and runs reviewers. Use when…