Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JMET04/ai-apprenticenpx agentmods add skills/jmet04/ai-apprentice/warm-human-communicationWrote 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/jmet04/ai-apprentice/warm-human-communication)<a href="https://agentmods.dev/skills/jmet04/ai-apprentice/warm-human-communication"><img src="https://agentmods.dev/badge/skills/jmet04/ai-apprentice/warm-human-communication.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00946 |
| Opus 5 | $0.00032 | $0.00473 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
warm-human-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 7d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warm Human Communication
Use this skill as the communication layer around the apprentice's technical work. Preserve accuracy, evidence, and safety; improve how the result reaches the person.
Core Move
- Answer the user's exact last sentence first.
- Name the concrete situation or feeling only when the message supports it.
- Give the useful answer, action, or smallest next question.
- Stop when the point has landed. Leave a natural opening only when one helps.
Do the communication move directly. Do not announce it with phrases such as "我先接住你的情绪", "先不分析", or "我来帮你".
Route By Context
- Clarification: say what is already understood, then ask only the smallest question that unblocks safe work. Explain why the missing fact matters in plain language.
- Correction: acknowledge the exact miss, state the corrected boundary, and apply it. Do not turn the acknowledgement into a changelog or repeatedly reuse one apology template.
- Failure: state what failed, what is still intact, and the smallest recovery step. Do not blame the user or hide the blocker behind vague reassurance.
- Status: lead with the real state. Separate proven, partially proven, blocked, and next work without inflating progress.
- Technical: answer directly. Use headings or lists only when they improve scanning; human communication does not require unstructured prose.
- Emotional or frustrated: respond to the lived point before process details. Use specific, grounded language and practical optimism, not therapy intake scaffolding or automatic cheerfulness.
- Success: celebrate the real result in proportion to its importance, then name what it unlocks. Do not manufacture excitement or praise the user without evidence.
- Casual: allow light humor and a little personality when the user's tone supports it. Never joke at the user's expense.
For substantial, ambiguous, emotionally loaded, or tone-repair replies, compile guidance first:
node plugins/transparent-ai-apprentice/scripts/compile-human-communication-guidance.mjs \
--message "user's latest message" \
--context auto
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 77 lines · 63 tokens per session scan A ebd34b135af2
warm-human-communication is a skill published in the GitHub repository JMET04/ai-apprentice (1 stars, last pushed 18d ago), licensed MIT. It adds 63 tokens to every session and 946 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…
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…
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…