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/giorgitarsaidze/idiolect/addgit clone --depth 1 https://github.com/GiorgiTarsaidze/idiolectWhat 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 | $0.00007 | $0.00144 |
| Opus 5 | $0.00003 | $0.00072 |
| Sonnet 5 | $0.00001 | $0.00029 |
| Haiku 4.5 | $0.00001 | $0.00014 |
Grade A, and why
add 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.
What it actually says
Run ${CLAUDE_PLUGIN_ROOT}/bin/idiolect.js add $ARGUMENTS and show the output.
If the word has no Latin hints (a non-Latin script word), ask the user how it is
spelled phonetically in Latin letters, then add each spelling with
${CLAUDE_PLUGIN_ROOT}/bin/idiolect.js hint <word> <spelling>.
Then tell them: dictate the word, and if it comes out wrong, run /idiolect:fix <word>.
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.
- 2d ago First seen · 14 lines · 7 tokens per session scan A 754575ad8c48
add is a command published in the GitHub repository GiorgiTarsaidze/idiolect (10 stars, last pushed 15d ago), licensed MIT. It adds 7 tokens to every session and 144 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.
Other commands, from other repositories
config
Configure voice-to-claude settings - model, hotkey, output mode.
start
Start the voice dictation daemon.
status
Check voice-to-claude daemon status and configuration.
stop
Stop the voice dictation daemon.
wheel-to-talk-stop
Stop the Wheel to Talk backend.
wheel-to-talk-setup
Enable voice dictation and start the Wheel to Talk backend.