context-and-decisions

context-and-decisions is a skill for Claude Code, Codex from Seekers2001/docs-governance. It costs 110 tokens per session (818 once invoked), scanned A, original, MIT.

A method for recording stable domain terms and difficult technical decisions in project documents. An ADR, or architecture decision record, is a short record of what was chosen, why, and what follows from it.

In plain words
What is it for?
It is for defining shared business vocabulary, resolving ambiguous terms, indexing architecture decisions, and recording alternatives, consequences, status, and exit paths.
Why use it?
It reduces repeated explanations and preserves the reasoning behind choices that may be hard to undo, such as database, authentication, deployment, or API-version decisions.

Skill for Claude CodeCodex

Part of the docs-governance plugin — 8 skills, 7 commands, 6 agents, 1 hook 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 skills/seekers2001/docs-governance/context-and-decisions
Any agent
npx skills add Seekers2001/docs-governance --skill context-and-decisions
Clone the repo
git clone --depth 1 https://github.com/Seekers2001/docs-governance

Made for: Claude Code, Codex.

Or install docs-governance, the plugin that ships this one along with the rest of its 8 skills, 7 commands, 6 agents, 1 hook.

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 context-and-decisions

README.md
[![agentmods](https://agentmods.dev/badge/skills/seekers2001/docs-governance/context-and-decisions.svg)](https://agentmods.dev/skills/seekers2001/docs-governance/context-and-decisions)
Your own site
<a href="https://agentmods.dev/skills/seekers2001/docs-governance/context-and-decisions"><img src="https://agentmods.dev/badge/skills/seekers2001/docs-governance/context-and-decisions.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 818 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 $0.00110 $0.00818
Opus 5 $0.00055 $0.00409
Sonnet 5 $0.00022 $0.00164
Haiku 4.5 $0.00011 $0.00082

Measured 5d ago against content hash 54be53afcc0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

context-and-decisions 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 5d 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.

skills/context-and-decisions/SKILL.md · 49 lines

What it actually says

领域上下文与决策

把“业务里这些词是什么意思”和“为什么选择这个方案”分开管理。没有稳定内容时不要创建空壳。

CONTEXT.md:只管领域语言

在术语反复解释、同词异义或模块边界因语言不清而出错时,使用 templates/context.example.md 懒创建根目录 CONTEXT.md

只记录:

  • 领域术语及精确定义;
  • 核心概念之间的关系;
  • 已确认的歧义与采用口径;
  • 仍待业务方确认的歧义。

禁止写入:实现细节、当前状态、任务排期、需求全文、决策理由和历史。对应内容分别回到代码/MAP、STATUS/Issue Tracker、Spec、ADR、LOG。术语必须能和代码、契约或业务证据对照;不能确认就标“待确认”,不要猜。

docs/adr/:一项决策一个文件

首次出现难回退决策时,创建:

  • docs/adr/README.md:薄索引,只列编号、标题、状态和链接;
  • 一项决策一份编号文件(例如 0001-use-postgresql.md),套用 templates/adr.example.md

使用连续四位编号。状态只允许 proposedaccepteddeprecatedsuperseded。ADR 至少包含:Context、Decision、Alternatives、Reason、Consequences、Status、Related、Supersedes。

以下变化默认检查是否需要 ADR:架构边界、数据库或存储、认证授权、部署拓扑、数据模型、API 版本策略、跨模块技术选型。普通实现细节、易回退的小改动和当天临时实验不要写 ADR。

决策流程

  1. 先读取现有 CONTEXT.mddocs/adr/README.md 和相关 ADR,避免重复决策。
  2. 用真实约束写 Context;列出确实讨论过的 Alternatives,不补写虚构方案。
  3. 在 Decision 与 Reason 中区分“选了什么”和“为什么选”。
  4. 在 Consequences 中写收益、代价、可逆性、迁移与退出路径;不可逆部分明确标出。
  5. 用 Related 链接 Spec/Issue、CONTRACT、TEST-ID、提交或代码位置。
  6. 新决策替代旧决策时,新 ADR 填 Supersedes,旧 ADR 改为 superseded 并互相链接;不要删除旧记录。
  7. 更新 docs/adr/README.md,并从 CLAUDE_MAP.md 只挂 ADR 索引入口,不枚举每个 ADR。
  8. PROJECT_LOG.md 追加一条决策事件。

排期与任务边界

让 GitHub Issues、Linear 或项目已有 Tracker 成为任务、状态、阻塞和排期的唯一事实源。只有项目没有外部 Tracker 时,才按项目约定使用本地 .scratch/;不要把排期塞进 CONTEXT.md、ADR、PROJECT_STATUS 或日志数据库。

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. 5d ago First seen · 49 lines · 110 tokens per session scan A 54be53afcc0c

Subscribe to this mod's changes

context-and-decisions is a skill published in the GitHub repository Seekers2001/docs-governance (33 stars, last pushed 23d ago), licensed MIT. It adds 110 tokens to every session and 818 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 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