agentmods.dev

king-context: Skill for Claude Code

.agents/skills/king-decisions/SKILL.md

king-decisions is a skill for Claude Code, Codex from deandevz/king-context. It costs 61 tokens per session (400 once invoked), scanned A, original, MIT.

A retrieval tool for indexed architectural decision records, or ADRs—documents that explain important project design choices. It searches current and historical decisions and can show how decisions changed.

In plain words
What is it for?
Use it to find why a technology or design was chosen, check whether a decision already exists, trace changes, or spot conflicts with a planned code change.
Why use it?
It answers architecture questions from recorded project decisions instead of guesswork or broad file scanning.

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 61 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-decisions/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-decisions

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/deandevz/king-context/king-decisions"><img src="https://agentmods.dev/badge/skills/deandevz/king-context/king-decisions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 400 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 $0.00061 $0.00400
Opus 5.5 $0.00024 $0.00160
Sonnet 5.5 $0.00012 $0.00080
Haiku 4.5 $0.00006 $0.00040

Measured 2mo ago against content hash d0ee13200a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

king-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 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-decisions/SKILL.md · 42 lines

What it actually says

King Decisions

Retrieve project architectural decisions through .king-context/bin/kctx adr.

Use this skill when the user asks about existing decisions, current architecture rationale, decision history, supersession, or conflicts with planned changes.

Goal

Answer from the minimum relevant decision context.

Behavior

Be direct and evidence-oriented. Cite ADR IDs. Prefer making a scoped retrieval attempt over asking for clarification when the topic is clear enough.

Rules

  • Prefer active ADRs for current guidance.
  • Use timeline when the user asks why something changed or when active results supersede older decisions.
  • Use historical ADRs only when they affect the answer.
  • If no ADR exists, say that no indexed decision was found. Do not invent one.
  • Do not scan or read .king-context/adr/*.md directly for retrieval. Use kctx adr status, kctx adr index, kctx adr search, kctx adr timeline, and kctx adr read.

Retrieval Budget

  • Start with .king-context/bin/kctx adr status; if stale, run .king-context/bin/kctx adr index before searching.
  • First call: .king-context/bin/kctx adr search "<topic>" --active --top 5
  • If enough: .king-context/bin/kctx adr read <ADR-ID> --preview or full read
  • If history matters: .king-context/bin/kctx adr timeline "<topic>"
  • Stop when the current decision and relevant history are clear.

Output

  • State the current decision first.
  • Mention superseded decisions only when relevant.
  • Cite ADR IDs.
  • Keep the answer concise.
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 · 42 lines · 61 tokens per session scan A d0ee13200a54

Subscribe to this mod's changes

king-decisions is a skill published in the GitHub repository deandevz/king-context (56 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 400 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.

Planning
Related

king-decisions compared with skills from other repositories

king-decisions next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
king-decisionsdeandevz/king-contextSkill565mo agoMITA61Claude 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