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.
git clone --depth 1 https://github.com/signalcompose/claude-toolsWrote 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/commands/signalcompose/claude-tools/speak)<a href="https://agentmods.dev/commands/signalcompose/claude-tools/speak"><img src="https://agentmods.dev/badge/commands/signalcompose/claude-tools/speak/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/commands/signalcompose/claude-tools/speak"><img src="https://agentmods.dev/badge/commands/signalcompose/claude-tools/speak.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 | $0.00007 | $0.00401 |
| Opus 5.5 | $0.00003 | $0.00160 |
| Sonnet 5.5 | $0.00001 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
speak scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
CVI Speak
テキストを CVI 設定に従って読み上げます。
実行経路: MCP tool（唯一の経路）
mcp__cvi-voice__speak を Skill tool 経由ではなくツール呼び出しとして即座に実行してください。引数:
text:$ARGUMENTSの内容voice: 省略可（CVI config の per-language voice が使われる）rate: 省略可（CVI config の SPEECH_RATE が使われる）
MCP server は Claude Code の sandbox 外で動作するため、dangerouslyDisableSandbox: true
は不要です。permission prompt も発生しません。
mcp__cvi-voice__speak が未登録、または呼び出しが失敗した場合は、MCP server の状態を
/cvi:check で診断してください。Bash fallback は存在しません（MCP 一本化、#242）。
結果表示
以下の形式でユーザーに表示してください（絵文字不可）:
Voice: "読み上げたテキスト"
- ツールの返り値は
Speaking: <text>形式。<text>部分を上の"読み上げたテキスト"に入れて表示する - CVI 無効（
CVI_ENABLED=off）のとき: MCP 経路はCVI is disabled. Enable with: /cvi:state onを文字列として返す。この場合はVoice: "..."ではなく、その案内文字列をそのまま表示する
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.
- 1mo ago First seen · 34 lines · 7 tokens per session scan A c285ac7bf832
speak is a command published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 401 once invoked, about $0.0000 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.