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 AratKruglik/claude-sdlc --skill architect-conventionsgit clone --depth 1 https://github.com/AratKruglik/claude-sdlcWrote 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/aratkruglik/claude-sdlc/architect-conventions)<a href="https://agentmods.dev/skills/aratkruglik/claude-sdlc/architect-conventions"><img src="https://agentmods.dev/badge/skills/aratkruglik/claude-sdlc/architect-conventions/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/aratkruglik/claude-sdlc/architect-conventions"><img src="https://agentmods.dev/badge/skills/aratkruglik/claude-sdlc/architect-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00806 |
| Opus 5 | $0.00032 | $0.00403 |
| Sonnet 5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
architect-conventions 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Conventions (shared)
Every development-phase architect follows these rules. Your own agent definition adds stack-specific detection, conventions, and verification commands on top — where the two conflict, your agent definition wins.
Hard rules
- Never delete files unless the spec explicitly asks for it.
- Never modify
.env,secrets/*, or~/.claude/**. - Never disable existing tests to "make them pass". Mark as skip with a code comment if you genuinely can't fix in scope, and report it in your summary.
- Never push branches or open PRs — that's the documentation phase's job.
- Never add a dependency not declared in the BA spec or required by your implementation. Justify additions in DECISIONS.
- Never edit lockfiles (
package-lock.json,yarn.lock,pnpm-lock.yaml,composer.lock,poetry.lock,uv.lock, etc.) by hand.
Code quality bar
- Follow existing patterns. Don't introduce a new way of doing things in scope of this feature.
- No
TODO/FIXMEcomments unless explicitly noting future work agreed upon by BA. - No commented-out code blocks.
- No "in case we need it later" abstractions. YAGNI.
- New deps via the project's package manager, pinned to a sane range (
^x.y.zor stack equivalent). Never*orlatest. - Match the existing styling/formatting approach. Don't introduce a new one.
Workflow steps
The orchestrator dispatches you in one of two passes: planning or implementation. Its base prompt tells you which pass you're in. In both:
- If
superpowersis installed (nosuperpowers_unavailableflag in CONTEXT), invokesuperpowers:using-superpowersvia the Skill tool to discover available skills. - Read the spec at
docs/plans/{task_slug}/01-business-analysis.md(plus any earlier-aspect outputs listed in your CONTEXT trailer). - Detect project shape per your agent definition's detection checklist.
- Explore the codebase — Glob/Grep for the most similar existing feature; Read actual files and mirror their naming and patterns.
- Read
CLAUDE.md— project conventions are sacred. - Implement. Use Edit for existing files, Write for new ones. Keep changes minimal.
- Invoke convention skills the orchestrator passed that are relevant to the task.
- Verify with your agent definition's stack-specific commands (build, type-check, lint). Failures block completion.
- If
superpowersis installed, invokesuperpowers:verification-before-completionvia the Skill tool before returning.
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.
- 8d ago First seen · 62 lines · 64 tokens per session scan A 0db460dd5afe
architect-conventions is a skill published in the GitHub repository AratKruglik/claude-sdlc (33 stars, last pushed 7d ago), licensed MIT. It adds 64 tokens to every session and 806 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…