omp-flow: Skill for Claude Code

.agents/skills/omp-flow-adr/SKILL.md

omp-flow-adr is a skill for Claude Code, Codex from Andyduck-ops/omp-flow. It costs 58 tokens per session (1,141 once invoked), scanned A, original, MIT.

A process for writing an ADR, or Architecture Decision Record: a short document that preserves why an important design choice was made. It stores these records in the repository's decision wiki.

In plain words
What is it for?
Use it to record architectural choices, constraints, rejected approaches, and small design decisions whose reasoning would be costly to rediscover.
Why use it?
It prevents future developers from removing or changing a deliberate design because the original reasoning was forgotten. It also records rejected alternatives that might otherwise be proposed again.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Andyduck-ops/omp-flow's own configuration. It tells Claude Code and Codex how to work on omp-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything omp-flow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Andyduck-ops/omp-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Andyduck-ops/omp-flow/main/.agents/skills/omp-flow-adr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Andyduck-ops/omp-flow

Made for: Claude Code, Codex.

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 omp-flow-adr

README.md
[![agentmods](https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-adr/github.svg)](https://agentmods.dev/skills/andyduck-ops/omp-flow/omp-flow-adr)
Your own site
<a href="https://agentmods.dev/skills/andyduck-ops/omp-flow/omp-flow-adr"><img src="https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-adr/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.

agentmods 80×15 button for omp-flow-adr

Your own site · 80×15
<a href="https://agentmods.dev/skills/andyduck-ops/omp-flow/omp-flow-adr"><img src="https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00058 $0.01141
Opus 5.5 $0.00023 $0.00456
Sonnet 5.5 $0.00012 $0.00228
Haiku 4.5 $0.00006 $0.00114

Measured 9d ago against content hash f14e6a6d577f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

omp-flow-adr 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 9d 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.

.agents/skills/omp-flow-adr/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OMP-Flow ADR

ADR here means Any Decision Record, as in MADR (Markdown Any Decision Records): the durable why behind how something is shaped. Records live in .omp-flow/wiki/decisions/. This Skill contains procedure only; decisions belong in the Wiki.

What deserves a record

Record a decision when its reasoning would be lost without it: a choice among real alternatives, an obvious approach that was rejected, a constraint, or a small design idea that a future agent would otherwise "simplify" back into a defect. Size does not matter; rediscovery cost does. Ask: if someone removed this tomorrow, would they know why it was there? A rejected idea also deserves a record, so it is not proposed again without new evidence.

Do not record restated code, Task progress, or an unconfirmed hypothesis.

Placement

.omp-flow/wiki/decisions/<context>--<question>--<YYYY-MM-DD>.md

<context> is the domain or bounded context and <question> is the stable problem the decision answers, both in kebab-case. The date comes last, so every record that has answered the same question sorts together. Do not number records; parallel branches would collide on the next number. Reuse an existing context and question name before inventing a new one.

Record

Write one decision per record. The four sections below are required, and each may be a single sentence. For a small decision, write in the spirit of a Y-Statement: in the context of , facing , we chose over to achieve , accepting .

---
type: "ADR"
title: "<question>: <choice>"
description: "<one sentence: under which constraint we chose what>"
tags: ["<context>", "<keyword>"]
status: "proposed"
date: "YYYY-MM-DD"
---

# <question>: <choice>

## Context and Problem Statement

## Considered Options

## Decision Outcome

Chosen option: "<option>", because <reason>.

## Confirmation

<The test, gate, or review that shows the decision still holds; write "none — relies on review"
when no mechanical check exists.>

Read the full file on GitHub · 108 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. 9d ago First seen · 108 lines · 58 tokens per session scan A f14e6a6d577f

Subscribe to this mod's changes

omp-flow-adr is a skill published in the GitHub repository Andyduck-ops/omp-flow (6 stars, last pushed 9d ago), licensed MIT. It adds 58 tokens to every session and 1,141 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.

Related

omp-flow-adr compared with skills from other repositories

omp-flow-adr next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
omp-flow-adrAndyduck-ops/omp-flowSkill69d agoMITA58Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code