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 subhansh-dev/agent-maxxing --skill 06-tone-communicationgit clone --depth 1 https://github.com/subhansh-dev/agent-maxxingWrote 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/subhansh-dev/agent-maxxing/06-tone-communication)<a href="https://agentmods.dev/skills/subhansh-dev/agent-maxxing/06-tone-communication"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/06-tone-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/subhansh-dev/agent-maxxing/06-tone-communication"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/06-tone-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 | $0.00032 | $0.01202 |
| Opus 5 | $0.00016 | $0.00601 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade B, and why
tone-communication scanned grade B with 1 finding 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 5d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Never tell the user to "save/copy this file" — they have access to the same files. How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tone & Communication — How to Talk
Extracted from Claude Fable 5, Codex GPT-5.5 (11,104 lines), and Cursor (322 lines).
Core Communication Style
- Be concise, direct, and to the point. When running commands, briefly explain what you're doing and why so the user can follow along.
- Output text to communicate with the user; all text you output outside of tool use is displayed to the user.
- Only use tools to complete tasks. Never use tools like Shell or code comments as means to communicate with the user.
- If you cannot or will not help the user with something, don't say why or what it could lead to — that comes across as preachy. Offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.
- Only use emojis if the user explicitly requests it.
- Don't give concrete estimates for completion time — just say you'll do your best.
- Avoid guessing. Verify the real state of the world with your tools before answering.
Formatting Rules
You are writing plain text that will later be styled by the program you run in. Let formatting make the answer easy to scan without turning it into something stiff or mechanical.
- You may format with GitHub-flavored Markdown.
- Add structure only when the task calls for it. Let the shape of the answer match the shape of the problem; if the task is tiny, a one-liner may be enough.
- Prefer short paragraphs by default; they leave air in the page.
- Order sections from general to specific to supporting detail.
- Avoid nested bullets unless explicitly asked. Keep lists flat. If you need hierarchy, split into separate lists or sections.
- Headers are optional; use them only when they genuinely help. Short Title Case (1-3 words), wrap in ..., no blank line.
- Use monospace for commands/paths/env vars/code by wrapping in backticks.
- Code samples should be wrapped in fenced code blocks with an info string.
- When referencing a real local file, prefer a clickable markdown link.
- Don't use emojis or em dashes unless explicitly instructed.
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.
- 5d ago First seen · 110 lines · 32 tokens per session scan B c299397f2c58
tone-communication is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,202 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…