adr-awareness

adr-awareness is a skill for Claude Code, Codex from nerds-odd-e/doughnut. It costs 94 tokens per session (1,180 once invoked), scanned A, original, MIT.

A guide for following accepted architectural decision records, or ADRs: documents that record approved technical choices for a project. It helps an agent read the relevant records and keep its work consistent with them.

In plain words
What is it for?
Use it when changing shared architecture, APIs, storage, authentication, packaging, monorepo layout, or conventions across multiple parts of a project.
Why use it?
It prevents architecture changes from silently contradicting decisions the team has already accepted and makes conflicts visible for human review.

Skill for Claude CodeCodex

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

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 skills/nerds-odd-e/doughnut/adr-awareness
Any agent
npx skills add nerds-odd-e/doughnut --skill adr-awareness
Clone the repo
git clone --depth 1 https://github.com/nerds-odd-e/doughnut

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 adr-awareness

README.md
[![agentmods](https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/adr-awareness.svg)](https://agentmods.dev/skills/nerds-odd-e/doughnut/adr-awareness)
Your own site
<a href="https://agentmods.dev/skills/nerds-odd-e/doughnut/adr-awareness"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/adr-awareness.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,180 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 5.1 $0.00094 $0.01180
Opus 5 $0.00047 $0.00590
Sonnet 5 $0.00019 $0.00236
Haiku 4.5 $0.00009 $0.00118

Measured 6d ago against content hash 3717b94b62a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

adr-awareness 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 6d 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/adr-awareness/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose: Humans own propose → discuss → approve (docs/adrs/README.md). Agents consume, cite, conflict-check, and help maintain records.

Output: Cited ADRs in reasoning and answers; conflict surfaced or human-owned exception noted; optional hygiene edits (index links, Superseded status) ending with ## ADR CHECK COMPLETE when invoked explicitly.

Path Role
docs/adrs/README.md Human playbook + index table
docs/adrs/_template.md Template for humans (do not invent process)
docs/adrs/*-accepted.md Current recommendations — primary input
docs/adrs/*-rejected.md History only
docs/adrs/NNNN-*.md without suffix Proposed — not binding yet

Always-current rule: Prefer Accepted ADRs. Treat Superseded and Rejected as archaeology unless the task is historical. If an Accepted ADR links to a superseding ADR, follow the newer one.

When this skill applies (architecture-shaped work):

  • Cross-cutting stack, persistence, API contracts, auth, packaging/monorepo layout, shared conventions across backend/frontend/cli/mcp/e2e
  • Explicit user mention of ADR / architecture decision
  • Change that would reverse or bypass an existing Accepted ADR

When it does not apply:

  • Local bugfix, copy, or single-module refactor with no architectural choice
  • Writing or approving a new ADR unless the human asked only for draft text for their proposal (they still announce, discuss, and approve)

Conflict policy (hybrid):

  • Default (agent alone): Do not implement an approach that conflicts with an Accepted ADR. Stop, cite the ADR, and ask how to proceed (follow ADR / human opens superseding ADR / human owns exception).
  • Human-owned exception: If the human explicitly accepts a deviation for this context, proceed and leave a trail (PR/commit message or note pointing at the ADR and the exception). Do not invent silent exceptions.
  • Not agreeing with an ADR is normal; that is not grounds for the agent to ignore it.

<preflight_gate name="load_index"> Read docs/adrs/README.md and list every Accepted ADR path from the index (and/or glob docs/adrs/*-accepted.md). If the directory is missing or empty except the meta ADR, continue with whatever Accepted files exist. </preflight_gate>

Read the full file on GitHub · 118 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. 6d ago First seen · 118 lines · 94 tokens per session scan A 3717b94b62a9

Subscribe to this mod's changes

adr-awareness is a skill published in the GitHub repository nerds-odd-e/doughnut (49 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,180 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens