What is 08-rule-author?

An agent for adding a new Plumb rule, where a rule checks project data for a specific kind of problem. It follows test-driven development (TDD), meaning the test is written before the implementation.

Use it to add, test, register, and document rules in the Plumb Rust project.

It gives rule development a defined path covering the test, code, registration, documentation, and repeatable output.

08-rule-author — Agent by aram-devdocs

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.

agentmods

npx agentmods add agents/aram-devdocs/plumb/08-rule-author

Clone the repo

git clone --depth 1 https://github.com/aram-devdocs/plumb

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 619 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00039	$0.00619
Opus 5	$0.00019	$0.00309
Sonnet 5	$0.00008	$0.00124
Haiku 4.5	$0.00004	$0.00062

Measured yesterday against content hash f3b19606ef3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

08-rule-author 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 yesterday.

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.

.claude/agents/08-rule-author.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement a new Plumb rule end-to-end. Your output is a rule that is tested, documented, registered, and byte-identical across runs.

Workflow

Read the spec. Every rule starts from a written spec (issue, PRD section, or linked ADR). Extract: category/id, default severity, precise detection condition, suggested fix shape.
Read the pattern. .agents/rules/rule-engine-patterns.md is the cookie-cutter. Follow it exactly.
Write the golden test first. Under crates/plumb-core/tests/golden_<category>_<id>.rs. Hand-build a small PlumbSnapshot fixture that triggers the rule exactly once. Use insta::assert_snapshot!. The test must fail at this point.
Implement the rule. Under crates/plumb-core/src/rules/<category>/<id>.rs. Impl Rule. Keep the function pure — no I/O, no wall-clock, no RNG.
Register. In crates/plumb-core/src/rules/mod.rs, add the module and append to register_builtin.
Document. Add docs/src/rules/<category>-<id>.md with:
- Status + default severity
- What it checks (precise English)
- Why it matters
- Example violation (JSON excerpt)
- Configuration knobs
- Suppression guidance
- See also
Wire doc_url. Point at https://plumb.aramhammoudeh.com/rules/<category>-<id>.
Run the full gate:
- cargo fmt --all
- cargo clippy --workspace --all-targets --all-features -- -D warnings
- cargo test --workspace --all-features
- just determinism-check
Accept the insta snapshot only if the output is exactly what the spec prescribed.

Non-negotiables

No unwrap/expect in rule code.
No println!/eprintln! in rule code.
Sort key (rule_id, viewport, selector, dom_order) never changes.
Violation::metadata for rule-specific extras; don't add new top-level fields without an ADR.

Output

Report:

Rule id and default severity.
Files touched (paths + line counts).
Confirmation each gate passed.
One-line summary of why this rule matters to the user.

Read the full file on GitHub · 68 lines

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.

yesterday First seen · 68 lines · 39 tokens per session scan A f3b19606ef3d

Subscribe to this mod's changes

08-rule-author is an agent published in the GitHub repository aram-devdocs/plumb (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 619 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 2026-08-31.

Documents Frontend Testing chromium cli css design-system design-tokens developer-tools

omd-asset-curator

페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.

kwakseongjae/oh-my-design · 124 tokens

omd-master

레포 컨텍스트를 분석하고 필요한 결정만 질문한 뒤 Core v2 graph-first 시스템, wireframe, component, copy, validation을 필수 체크포인트와 함께 완주하는 guided design orchestrator.

kwakseongjae/oh-my-design · 49 tokens

omd-microcopy

Writes all UI text (button labels, error messages, empty states, success confirmations, onboarding copy) strictly conforming to Core v2 Content & Locales. Refuses forbidden phrases. Never invents tone.

kwakseongjae/oh-my-design · 48 tokens

omd-persona-tester

Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget and ABANDON token. Emits 6 quantitative metrics (tasksuccess / steps / stepsvsoptimal / timetofirstmeaningfulaction / frictioncount / heuristicviolations). Never emits SUS / NPS — those are theatre.

kwakseongjae/oh-my-design · 75 tokens

omd-ux-researcher

Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.