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 alexey-pkv/claude-companions --skill tonegit clone --depth 1 https://github.com/alexey-pkv/claude-companionsWrote 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/alexey-pkv/claude-companions/tone)<a href="https://agentmods.dev/skills/alexey-pkv/claude-companions/tone"><img src="https://agentmods.dev/badge/skills/alexey-pkv/claude-companions/tone/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/alexey-pkv/claude-companions/tone"><img src="https://agentmods.dev/badge/skills/alexey-pkv/claude-companions/tone.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 | $0.00048 | $0.00538 |
| Opus 5.5 | $0.00019 | $0.00215 |
| Sonnet 5.5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
tone 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.
What it actually says
Tone Selection
Switch or randomize the communication tone/personality for the current session. Tones are stored as .md files in ~/.claude/tones/.
Handling Arguments
Parse $ARGUMENTS and follow one of three paths:
Path 1: List available tones
If $ARGUMENTS is empty, not provided, "list", or "ls":
- Use Bash:
ls ~/.claude/tones/*.md 2>/dev/null | xargs -n1 basename | sed 's/\.md$//' | sort - Display the results as a formatted list
- Do NOT apply any tone — just show the list
Path 2: Random tone selection
If $ARGUMENTS is "random":
- Use Bash:
~/.claude/scripts/rotate-tone.sh - Adopt the output as the tone for the rest of the session
Path 3: Specific tone
If $ARGUMENTS is a tone name (e.g., "space-marine", "gordon-ramsay"):
- Read
~/.claude/tones/$ARGUMENTS.md - If found, confirm to the user which tone was loaded
- Adopt the tone's communication style for the rest of the session
If the tone is not found:
- Use Bash to list available tones:
ls ~/.claude/tones/*.md 2>/dev/null | xargs -n1 basename | sed 's/\.md$//' | sort - Check if any available tone name is similar to what the user typed (e.g., "ramsay" → "gordon-ramsay", "marine" → "space-marine"). If there's a likely match, suggest it: "Did you mean
<tone-name>?" - If no close match, show the available tones list and suggest: "You can create a custom tone with
/create-tone $ARGUMENTS"
After Loading a Tone
- Tell the user the tone name that was loaded
- Immediately begin using the tone's communication style
- Maintain the tone for all subsequent responses in the session
- The tone affects ONLY communication style — never compromise code quality, technical accuracy, or professionalism in code/architecture
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.
- 2mo ago First seen · 49 lines · 48 tokens per session scan A 298e06de5038
tone is a skill published in the GitHub repository alexey-pkv/claude-companions (5 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 538 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 2026-08-31.
tone compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tonealexey-pkv/claude-companions | Skill | 5 | 4mo ago | MIT | A | 48 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |