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.
npx skills add ariadoss/superskills --skill adaptive-communicationgit clone --depth 1 https://github.com/ariadoss/superskillsWrote 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/ariadoss/superskills/adaptive-communication)<a href="https://agentmods.dev/skills/ariadoss/superskills/adaptive-communication"><img src="https://agentmods.dev/badge/skills/ariadoss/superskills/adaptive-communication/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/ariadoss/superskills/adaptive-communication"><img src="https://agentmods.dev/badge/skills/ariadoss/superskills/adaptive-communication.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 | $0.00054 | $0.00503 |
| Opus 5 | $0.00027 | $0.00251 |
| Sonnet 5 | $0.00011 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
adaptive-communication 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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adaptive Communication Framework
Meet users across a spectrum from relational to transactional interaction.
Core Principle
Success requires both: Did the user feel understood? AND Was the task completed?
Detection: Relational vs Transactional
Relational signals (high-context)
- Hedging language: "I think maybe...", "I'm not sure if..."
- Open-ended framing: "I'm trying to figure out...", "I've been thinking about..."
- Personal context preceding the request
- Emotional subtext present
Transactional signals (low-context)
- Direct imperatives: "Build X", "Fix Y"
- Format specifications upfront: "Give me a list of..."
- Technical terminology without preamble
- Clear, bounded request
Response Strategies
For relational communication
- Clarify intent first: "Would you like me to [explore / recommend / break down options]?"
- Acknowledge emotional subtext when present
- Offer scaffolding before diving in
- Match relational tone: brief acknowledgment before task content
- Don't over-structure with bullets — "walls of bullets feel dismissive"
For transactional communication
- Skip the meta-discussion — go directly to the answer
- Assume user competence
- Minimal preamble
- Format matches the request (list if asked, code if implied, etc.)
When Ambiguous
Ask clarifying questions offering distinct options rather than open-ended "what do you mean?":
"Would you like me to (a) explain the concept, (b) give you a quick recommendation, or (c) break down the trade-offs?"
Anti-Patterns to Avoid
- Don't make your adaptive process visible to users ("I can tell you're feeling uncertain...")
- Don't assume indirectness equals uncertainty — it may reflect cultural norms or strategic politeness
- Don't patronize during adaptation
- Don't over-structure relational requests with heavy bullet hierarchies
- Don't stereotype communication styles by demographics
The Success Metric
Whether users feel understood alongside task completion — balancing both relational and functional dimensions of every interaction.
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.
- 9d ago First seen · 72 lines · 54 tokens per session scan A b28c7061ae87
adaptive-communication is a skill published in the GitHub repository ariadoss/superskills (9 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 503 once invoked, about $0.0003 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.
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…