speak

A command that sends the most recent assistant reply to a text-to-speech service and reads it aloud. It removes formatting and code so the result sounds like natural spoken English.

In plain words
What is it for?
Use it after a response when you want that response spoken aloud, including replies containing headings, lists, tables, or code.
Why use it?
It provides audio for a reply without requiring you to copy and clean up the text yourself. It also avoids reading tool output or other hidden conversation details.

Command

Install

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.

agentmods
npx agentmods add commands/fakoli/fakoli-plugins/speak
Clone the repo
git clone --depth 1 https://github.com/fakoli/fakoli-plugins
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00265
Opus 5 $0.00004 $0.00133
Sonnet 5 $0.00002 $0.00053
Haiku 4.5 $0.00001 $0.00026

Measured 2d ago against content hash 0ebe9aa4edfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

plugins/fakoli-speak/commands/speak.md · 30 lines

What it actually says

Look at your most recent assistant response in this conversation — the one immediately before the user typed /speak.

Extract ONLY the visible text you wrote to the user. Exclude:

  • Tool call inputs/outputs, raw JSON, system reminders, session metadata
  • Markdown syntax: #, *, `, |, ---, ```, >,
  • Code blocks and their contents
  • Table grid characters (keep the data as prose)

Rewrite the extracted content as natural spoken English:

  • Tables become conversational summaries ("The S&P 500 closed at 648, down 1.7 percent...")
  • Bullet points become flowing sentences
  • Numbers stay as-is but spell out symbols (% becomes "percent", $ stays)
  • Section headers become topic transitions ("Regarding the macro dashboard...")
  • Skip anything that wouldn't make sense spoken aloud

Then send the text to TTS using a heredoc (safe for quotes, dollars, backticks):

cd ${CLAUDE_PLUGIN_ROOT} && uv run fakoli-speak speak <<'SPEAK_EOF'
your cleaned spoken text here
SPEAK_EOF

After running the command, respond with only: "Speaking." — nothing else.

Changes

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.

  1. 2d ago First seen · 30 lines · 8 tokens per session scan A 0ebe9aa4edfc

Subscribe to this mod's changes

speak is a command published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 24d ago), licensed MIT. It adds 8 tokens to every session and 265 once invoked, about $0.0000 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.