Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add iamcxa/kc-claude-plugins/plugin install kc-team-opsWrote 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/iamcxa/kc-claude-plugins/decision-debate)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/decision-debate"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/decision-debate/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/iamcxa/kc-claude-plugins/decision-debate"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/decision-debate.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 | $0.00036 | $0.01534 |
| Opus 5 | $0.00018 | $0.00767 |
| Sonnet 5 | $0.00007 | $0.00307 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
decision-debate 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Debate - Structured Approach Evaluation
Overview
Structured debate for technical decisions — eliminates confirmation bias and surfaces blind spots.
Announce: "I'm using the decision-debate skill to evaluate these approaches."
Setup:
Read → ${CLAUDE_PLUGIN_ROOT}/reference/decision-debate-reference.mdRead → ${CLAUDE_PLUGIN_ROOT}/reference/learned-patterns.md(Debate Patterns section — public, curated)Read → ~/.claude/kc-plugins-config/learned-patterns-local/kc-team-ops.md(Debate Patterns section — local, raw; optional/may not exist yet)
Step 0: Triage
Before starting a debate, assess whether one is warranted.
| Signal | Action |
|---|---|
| Single clear criterion decides it (e.g., "does it re-render?") | Answer directly — no debate |
| Well-known pattern with consensus best practice | Answer directly, cite the pattern |
| User asks "which should I use" on a trivial choice | Answer directly — debate is overkill |
| User's tool/framework has an opinionated default (e.g., RHF → uncontrolled) | Answer directly, explain the default + edge cases |
| Genuine trade-offs with 2+ weighted criteria | → Step 1 (debate) |
| Architectural decision with long-term consequences | → Step 1 (debate) |
| User says "stress-test", "challenge", "devil's advocate" | → Step 1 with Devil's Advocate variant |
Rule: If you can answer confidently in <5 sentences with no trade-off tension, skip the debate. The skill exists for decisions where reasonable engineers disagree, not for knowledge questions.
Step 1: Frame
State clearly before proceeding:
- Context: What problem are we solving?
- Approaches: 2-4 options (if user provides only 1, generate the strongest alternative)
- Criteria: What matters?
GATE: All three elements confirmed before Step 2. Missing criteria or alternatives → ask the user, do not infer.
Variant Selection
| Variant | Trigger | Process |
|---|---|---|
| Quick Debate | 2 approaches, ≤3 criteria, reversible decision | 2 advocates, Main synthesizes (no evaluator) |
| Standard | 2-3 approaches, multiple criteria, moderate impact | 2-3 advocates + Staff Engineer evaluator |
| Deep Debate | 3+ approaches OR security/perf/compliance implications | Advocates + specialist reviewers + evaluator |
| Devil's Advocate | User leans one way ("I'm going with X, but...") | 1 strong contrarian + evaluator (see Devil's Advocate Rules below) |
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.
- 6d ago First seen · 127 lines · 36 tokens per session scan A 7f582518929b
decision-debate is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,534 once invoked, about $0.0002 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 2026-09-03.
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…