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 smixs/disruptor-skills --skill architecture-guardrailsgit clone --depth 1 https://github.com/smixs/disruptor-skillsWrote 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/smixs/disruptor-skills/architecture-guardrails)<a href="https://agentmods.dev/skills/smixs/disruptor-skills/architecture-guardrails"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/architecture-guardrails/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/smixs/disruptor-skills/architecture-guardrails"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/architecture-guardrails.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 | $0.00030 | $0.02161 |
| Opus 5 | $0.00015 | $0.01081 |
| Sonnet 5 | $0.00006 | $0.00432 |
| Haiku 4.5 | $0.00003 | $0.00216 |
Grade A, and why
architecture-guardrails 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 12d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture guardrails prompt for a web project
Stage contract
- Stage: 3. Architecture guardrails · Kind: prompt
- Inputs: the spec (stage 2) + the chosen stack.
- Outputs: module/import boundaries made executable — enforced by linter + import-graph + filesystem checks in CI, not by prose an agent can ignore.
- Entry gate: the spec exists; you're about to stand up structure agents will erode.
- Done when: the boundaries are machine-checked in CI (a violation fails the build).
- Next: the
slicing-into-tracer-bulletsskill. - Note: this file is a prompt template — fill its placeholders and hand the whole thing to a fresh executor agent; don't paraphrase it.
Purpose
This document is a neutral template for future web projects developed with an AI agent. Its job: fix the architecture, module boundaries, contract rules, and automatic checks up front, so the agent does not erode the project's structure as development proceeds.
The architecture below is one proven option for production-grade web projects: DDD modules, vertical slices, ports/adapters, contract boundaries, and executable architecture via linters, an import graph, and CI checks.
Architectural model
- The project is divided into bounded contexts: large domain modules, each with its own responsibility.
- Inside each module, scenarios are laid out as vertical slices: one use case holds its orchestration logic, tests, and public entry point.
- Applications stay thin composition roots: they bring up the runtime, config, and dependencies and wire in the modules, but contain no business logic.
- The shared technical platform contains only cross-cutting capabilities: config, database, auth primitives, HTTP baseline, queues, storage, observability, testing.
- Modules must not import each other's internals directly. Communication goes only through explicitly published contracts.
- Architecture counts as part of the code: compliance is verified by a linter, an import graph, filesystem checks, tests, and CI.
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.
- 12d ago First seen · 237 lines · 30 tokens per session scan A 6971a443f46f
architecture-guardrails is a skill published in the GitHub repository smixs/disruptor-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 2,161 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
github-actions
Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…
neon
Use when you have picked Neon (serverless Postgres) and need to connect correctly from a serverless or edge runtime, wire database branching into dev, preview and CI, or stop being burned by scale-to-zero cold starts and pooler limits — including choosing HTTP versus WebSocket connections and pooled versus direct…
render
Use when deploying or fixing an app on Render — web services, background workers, cron jobs, private services, managed Postgres and Key-Value, and especially the render.yaml Blueprint. Covers deploys that fail with no open ports detected, 502s on first deploy, free-tier cold starts, and a free Postgres about to expire…
integrating-sast-into-github-actions-pipeline
This skill covers integrating Static Application Security Testing (SAST) tools—CodeQL and Semgrep—into GitHub Actions CI/CD pipelines. It addresses configuring automated code scanning on pull requests and pushes, tuning rules to reduce false positives, uploading SARIF results to GitHub Advanced Security, and…
verifying-build-provenance-with-slsa-sigstore
Verify signed artifacts and SLSA build provenance with Sigstore cosign and slsa-verifier, enforce keyless OIDC identity, and apply SLSA Build levels to harden the software supply chain.
continuous-llm-red-teaming-with-promptfoo
Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.