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 skills add Netcracker/qubership-ai-packages --skill adr-authoringgit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/adr-authoring)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/adr-authoring"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/adr-authoring/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/netcracker/qubership-ai-packages/adr-authoring"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/adr-authoring.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 | $0.00101 | $0.00824 |
| Opus 5 | $0.00051 | $0.00412 |
| Sonnet 5 | $0.00020 | $0.00165 |
| Haiku 4.5 | $0.00010 | $0.00082 |
Grade A, and why
adr-authoring 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 11d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring an ADR
You already know the ADR genre. This skill only pins the local conventions our repositories enforce, so the record you write fits the contract on the first try.
What belongs in an ADR
One decision per record. Reach for an ADR when a choice affects structure (for example a pattern such as microservices), a non-functional requirement (security, availability, fault tolerance), a dependency, a published interface or API, or a construction technique (a library, framework, or tool). A rough test: if the decision needed a meeting to settle, it is worth recording.
Local conventions
These are the parts the generic ADR format does not pin down:
- Location — store the file under
docs/adr/in the same repository. ADRs are public unless an exception is approved. - Filename — lowercase with dashes and a 4-digit prefix:
0002-tool-for-password-management.md. Pick the next free number by scanning the existing files indocs/adr/; start at0001if the folder is empty. - Status — one of
Proposed,Accepted,Rejected,Superseded. A new record starts asProposed; only setAcceptedonce the team has signed off. - Date — ISO 8601 (
2025-02-16), and only the date the decision was accepted. Leave it blank while the status isProposed. - Immutability — an accepted ADR is final. To change a decision, write a new
ADR rather than editing the old one. Link the two in both directions under
Related ADRs, and in the new record's Consequences note that it
supersedes the old one and why. Set the old record's status to
Superseded.
Template
Fill this exact structure. Keep the #### heading levels — the metadata block
relies on them.
# <Architecture Decision Title>
## Status
<Proposed | Accepted | Rejected | Superseded>
#### Date
<ISO 8601 date the decision was accepted; blank while Proposed>
#### Owner
<GitHub account of the person responsible for this ADR>
#### Participants and approvers
<Teams and GitHub accounts involved in the decision>
#### Related ADRs
<Links to related or superseded ADRs, if any>
## Context
<Problem statement and the forces at play — technical, organizational, project-specific. A value-neutral description of the facts.>
## Decision
<The decision, in active voice: "We will...">
### Justification
<Why this option won, which alternatives were considered, and why they were rejected.>
## Consequences
<The resulting context — positive, negative, and neutral effects on the team and project.>
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.
- 11d ago First seen · 83 lines · 101 tokens per session scan A 9c3da44dca8b
adr-authoring is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 101 tokens to every session and 824 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…