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 agentmods add skills/aarvion-ai/stackwise-skills/engineering-rulesnpx skills add Aarvion-AI/stackwise-skills --skill engineering-rulesgit clone --depth 1 https://github.com/Aarvion-AI/stackwise-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/aarvion-ai/stackwise-skills/engineering-rules)<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/engineering-rules"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/engineering-rules.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.01378 |
| Opus 5 | $0.00059 | $0.00689 |
| Sonnet 5 | $0.00023 | $0.00276 |
| Haiku 4.5 | $0.00012 | $0.00138 |
Grade A, and why
engineering-rules 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Rules
Turns Claude into the repo's staff engineer: every diff it produces already passes the review these seven rules describe.
When to Use This Skill
- Implementing any feature, fix, or refactor, in any language
- Self-reviewing a diff before commit or PR
- Cleaning up AI-generated or copy-pasted code
- Writing code samples for skills, docs, or references
- Reviewing someone else's PR against repo standards
- Deciding whether to extract, inline, or delete code
Core Workflow
- Search before writing. Grep the codebase for an existing helper, component, or util that already does the job (search by domain nouns and verbs, not just exact names). Reuse or extend it; only write new code when nothing fits.
- Implement. Small single-responsibility units, follow the project's existing structure and idioms, configuration over hardcoded values, no new global state.
- Run the rules checklist over the diff (the seven rules below, each is concrete and checkable):
- Rule 1, Reusable: no copy-paste variants; shared shape appearing a second time is extracted.
- Rule 2, Maintainable: units small, module boundaries clear, dependencies point one way, nothing hardcoded that belongs in config.
- Rule 3, Readable: intention-revealing names (no
data,tmp,handle,process2), early returns over nesting, reads top-down. - Rule 4, No AI slop: scan the diff against
references/ai-slop-checklist.mditem by item. - Rule 5, Dead code: everything your change made unreachable is deleted; zero commented-out code; orphaned exports removed.
- Rule 6, Comments: every comment states a non-obvious why; any comment narrating what gets deleted or the code gets rewritten.
- Rule 7, No em dashes:
grep -rn "$(printf '\xe2\x80\x94')"over changed files, in code, comments, docs, and commit messages; returns nothing.
- Fix all violations and re-run the checklist until clean. A single pass is never assumed sufficient; fixes for one rule often introduce violations of another.
- Run the project's formatter and linter (e.g.
prettier --check .+eslint .,ruff format --check && ruff check,gofmt -l . && go vet ./...); fix every reported issue and re-run until clean. - Verify behavior. Run the project's tests for the touched area; debug failures before declaring done.
What ships with it
4 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.
- 3d ago First seen · 92 lines · 0 tokens per session scan A 9b556694133e
engineering-rules is a skill published in the GitHub repository Aarvion-AI/stackwise-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 117 tokens to every session and 1,378 once invoked, about $0.0006 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
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
brand-docx
Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.