agentmods.dev

king-context: Skill for Claude Code

.agents/skills/king-record-decision/SKILL.md

king-record-decision is a skill for Claude Code, Codex from deandevz/king-context. It costs 53 tokens per session (481 once invoked), scanned A, original, MIT.

A workflow for creating and maintaining architecture decision records (ADRs), which are project documents explaining important technical choices and their reasons.

In plain words
What is it for?
Use it to create, link, supersede, index, and validate ADRs through the project's decision-record command-line tool.
Why use it?
It helps keep past decisions organized, connected, and up to date when a project changes direction.

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 deandevz/king-context's own configuration. It tells Claude Code and Codex how to work on king-context 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 king-context configures →

not rated 56repo 5mo ago A scan 53 tokens original MIT
View source ↗ deandevz/king-context
Reuse

Borrowing it

Nothing to install: this file belongs to deandevz/king-context. 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/deandevz/king-context/main/.agents/skills/king-record-decision/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/deandevz/king-context

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 king-record-decision

README.md
[![agentmods](https://agentmods.dev/badge/skills/deandevz/king-context/king-record-decision/github.svg)](https://agentmods.dev/skills/deandevz/king-context/king-record-decision)
Your own site
<a href="https://agentmods.dev/skills/deandevz/king-context/king-record-decision"><img src="https://agentmods.dev/badge/skills/deandevz/king-context/king-record-decision/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 king-record-decision

Your own site · 80×15
<a href="https://agentmods.dev/skills/deandevz/king-context/king-record-decision"><img src="https://agentmods.dev/badge/skills/deandevz/king-context/king-record-decision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 481 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 $0.00053 $0.00481
Opus 5.5 $0.00021 $0.00192
Sonnet 5.5 $0.00011 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 2mo ago against content hash a6e55f4280b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

king-record-decision 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 2mo 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/king-record-decision/SKILL.md · 54 lines

What it actually says

King Record Decision

Create and maintain project ADRs through .king-context/bin/kctx adr.

Goal

Create a valid ADR, link related or superseded decisions, rebuild the decision index, and validate the result.

Behavior

Be careful and decisive. The CLI provides structure; you provide judgment about relationships between decisions. Ask the user only when a new decision would conflict with an active ADR and the replacement is not explicit.

Before Creating

  • Start with .king-context/bin/kctx adr status; if stale, run .king-context/bin/kctx adr index.
  • Search active decisions for the topic.
  • Search active decisions for key technologies or architecture areas.
  • Read previews for likely matches.
  • Use timeline if a previous decision may be superseded.
  • Do not scan .king-context/adr/*.md to discover related decisions. Discovery must happen through kctx adr retrieval commands.

Classify Existing ADRs

  • superseded-by-new: the new decision replaces this ADR.
  • related: the ADR is relevant but still valid.
  • conflict: the new decision appears to contradict an active ADR and needs user confirmation.
  • irrelevant: do not link.

Creation Rules

  • If the new decision replaces an old one, use --supersedes and include a concrete supersession reason.
  • If the new decision only touches nearby architecture, use --related.
  • If there is an unresolved conflict with an active ADR, ask the user before writing.
  • If no related ADR exists, create an independent ADR.
  • Read or edit ADR markdown only when creating a new ADR or updating a specific ADR selected by the workflow.

Validation

  • After writing markdown, run .king-context/bin/kctx adr index.
  • Run .king-context/bin/kctx adr validate.
  • Run .king-context/bin/kctx adr timeline "<topic>" and summarize the resulting state.

Output

  • Name the ADR created.
  • List superseded and related ADRs.
  • State whether validation passed.
  • Include any remaining conflict or ambiguity.
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. 2mo ago First seen · 54 lines · 53 tokens per session scan A a6e55f4280b6

Subscribe to this mod's changes

king-record-decision is a skill published in the GitHub repository deandevz/king-context (56 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 481 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 2026-08-30.

PlanningWriting and docs
Related

king-record-decision compared with skills from other repositories

king-record-decision next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
king-record-decisiondeandevz/king-contextSkill565mo agoMITA53Claude 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.jsSkill143ktodayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143ktodayMITA103Claude Code