pattern-compliance

pattern-compliance is an agent for coding agents from optimiziramsi/skills. It costs 126 tokens per session (1,317 once invoked), scanned A, original, MIT.

A read-only review that compares recent code changes with the project's formal pattern registry in .agent/patterns/. The registry contains approved ways to structure recurring kinds of code.

In plain words
What is it for?
Use it to audit changed files or selected pattern topics and report where the implementation does not follow the registry's checklists and rules.
Why use it?
It catches changes that conflict with the repository's explicit design patterns, including patterns marked as decided or still to be resolved.

Agent

Part of the optimiziramsi-skills plugin — 24 skills, 24 commands, 9 agents, 2 hooks shipped together

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/optimiziramsi/skills/pattern-compliance
Clone the repo
git clone --depth 1 https://github.com/optimiziramsi/skills

Or install optimiziramsi-skills, the plugin that ships this one along with the rest of its 24 skills, 24 commands, 9 agents, 2 hooks.

Wrote 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.

agentmods badge for pattern-compliance

README.md
[![agentmods](https://agentmods.dev/badge/agents/optimiziramsi/skills/pattern-compliance.svg)](https://agentmods.dev/agents/optimiziramsi/skills/pattern-compliance)
Your own site
<a href="https://agentmods.dev/agents/optimiziramsi/skills/pattern-compliance"><img src="https://agentmods.dev/badge/agents/optimiziramsi/skills/pattern-compliance.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,317 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.

ModelPer sessionOnce invoked
Fable 5 $0.00126 $0.01317
Opus 5 $0.00063 $0.00659
Sonnet 5 $0.00025 $0.00263
Haiku 4.5 $0.00013 $0.00132

Measured 3d ago against content hash 7b63d21c9374, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pattern-compliance 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.

patterns/agents/pattern-compliance.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the read-only pattern-compliance auditor. You read changed code and the relevant .agent/patterns/<topic>.md bodies and report whether the code complies. You never edit code.

Inputs

One of:

  • A git ref range (e.g. HEAD~5..HEAD or <integration>..feature-branch).
  • A list of file paths to audit.
  • A list of pattern topics to audit against.
  • "Since session start" → derive the changed-files list from git log --since=... --name-only --pretty=format:"".

If the orchestrating session didn't specify, default to: changed files in the last 5 commits on the current branch, audited against every pattern they touch.

Required reading (in order)

  1. .agent/patterns/README.md — the registry index and its gating rule. Internalize it before reading topic bodies. Code that follows a decided or TODO pattern is a violation REGARDLESS of how well it matches the body.
  2. Each relevant .agent/patterns/<topic>.md, checklist-first. Every blessed body opens with #### Rules — write-time checklist — diff-check the changed code against EVERY checklist line first (it's the distilled rubric), then read the full body (GOOD/BAD/Anti-patterns/Edge cases) for the suspects the checklist surfaced and any judgment call a one-liner can't settle. Never checklist-only-skim a pattern the code clearly centers on.
  3. Each changed file fully. Don't grep — semantic shape matters.

How to pick which patterns to audit against

Authoritative first step: match each changed file's repo-relative path against .agent/patterns/pattern-routes.tsv (columns: glob → pattern → status → route; generated from every pattern's paths: frontmatter). Every matching pattern — edit AND land routed — is in scope.

If a changed file matches nothing in the routes table but clearly implements a distinct code shape, name the shape you see and grep .agent/patterns/ for a matching body. If none exists, that's a finding — the code implements an unregistered shape (walk it via the manage-patterns skill before it lands); don't invent which pattern applies.

Read the full file on GitHub · 109 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.

  1. 3d ago First seen · 109 lines · 126 tokens per session scan A 7b63d21c9374

Subscribe to this mod's changes

pattern-compliance is an agent published in the GitHub repository optimiziramsi/skills (2 stars, last pushed 14d ago), licensed MIT. It adds 126 tokens to every session and 1,317 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.

Related

Other agents, from other repositories

spec-compliance-reviewer

Agent Spec Compliance Reviewer — vérifie indépendamment que chaque Acceptance Criteria (AC) de chaque US est implémentée dans le code matérialisé. Re-lit le code sans faire confiance au rapport dev-, sur le pattern "Do not trust the report" (superpowers v5.1). Produit spec-compliance.{md,json} avec verdict 🟢/🟡/🔴…

zekiriabd/SDD-Pro · 104 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

code-quality-reviewer

Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).

babyworm/rtl-agent-team · 62 tokens

audit-geo

Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).

XuanRanL/loamwright-SEO-Skill · 44 tokens

ui-visual-validator

Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.

Dicklesworthstone/pi_agent_rust · 54 tokens

investigative-reporter-agent

Takes a story spark and produces a fully-scoped investigation package — editorial angle, source map, records requests, document analysis, verification checklist, libel-risk flags, and a draft lede — ready for an editor's desk.

ur-grue/autopunk-media-skills · 6 tokens