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 agentmods add commands/pchalasani/claude-code-tools/speakgit clone --depth 1 https://github.com/pchalasani/claude-code-toolsWhat 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 | $0.00000 | $0.00338 |
| Opus 5 | $0.00000 | $0.00169 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
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 yesterday.
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
Enable, disable, or configure voice feedback.
Commands:
/speak- Enable voice feedback with current voice/speak <voice>- Set voice (e.g., azure, alba) and enable feedback/speak stop- Disable voice feedback/speak prompt <text>- Set custom instruction for voice summaries/speak prompt- Clear custom prompt
Config file: ~/.claude/voice.local.md
---
voice: azelma
enabled: true
prompt: "always end with 'peace out'"
---
Behavior:
- When no argument: Set
enabled: trueand tell user: "Voice feedback enabled. Use/speak stopto disable, or/speak <name>to change voice." - When voice name given: Set
voice: <name>andenabled: true, tell user: "Voice set to and enabled. Use/speak stopto disable." - When
stop: Setenabled: falseANDjust_disabled: true(voice unchanged), tell user: "Voice feedback disabled. Use/speakto re-enable." - When
prompt <text>: Setprompt: <text>, tell user: "Custom prompt set: " - When
prompt(no text): Clear the prompt field, tell user: "Custom prompt cleared."
Create the config file if it doesn't exist (default voice: azelma).
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.
- yesterday First seen · 38 lines · 0 tokens per session scan A 66d316ede85a
speak is a command published in the GitHub repository pchalasani/claude-code-tools (1,986 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 338 tokens. 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 2026-08-30.
Other commands, from other repositories
multi-stage-issue-review
Issue記載内容の多段階レビュー（通常→影響範囲）×2回と指摘対応を自動実行.
issue-enhance
Issue内容を分析し、ユーザーに質問しながら不足情報を補完・更新.
issues-exec-plan
複数Issueの並列作業可否を分析し、実行計画をまとめるエピックIssueを作成.
pr-merge-pipeline
複数IssueのPR作成→CI通過→順次マージ→統合検証を自動化.
worktree-cleanup
Command "worktree-cleanup" from Kewton/CommandMate, covering worktree cleanup スキル, 概要, 使用方法, 実行内容 and パラメータ.
cause-analysis
Issue記載の事象から根本原因を分析し原因と対策案をIssueに追記.