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.
curl -O https://raw.githubusercontent.com/Andyduck-ops/omp-flow/main/.agents/skills/omp-flow-adr/SKILL.mdgit clone --depth 1 https://github.com/Andyduck-ops/omp-flowWrote 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/andyduck-ops/omp-flow/omp-flow-adr)<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.
<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>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 | $0.00058 | $0.01141 |
| Opus 5.5 | $0.00023 | $0.00456 |
| Sonnet 5.5 | $0.00012 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
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.
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.>
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.
- 9d ago First seen · 108 lines · 58 tokens per session scan A f14e6a6d577f
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.
omp-flow-adr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omp-flow-adrAndyduck-ops/omp-flow | Skill | 6 | 9d ago | MIT | A | 58 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |