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/shreyas-s-rao/claude-code-narratorWrote 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/shreyas-s-rao/claude-code-narrator/hush)<a href="https://agentmods.dev/commands/shreyas-s-rao/claude-code-narrator/hush"><img src="https://agentmods.dev/badge/commands/shreyas-s-rao/claude-code-narrator/hush/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/shreyas-s-rao/claude-code-narrator/hush"><img src="https://agentmods.dev/badge/commands/shreyas-s-rao/claude-code-narrator/hush.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 | $0.00270 |
| Opus 5 | $0.00003 | $0.00135 |
| Sonnet 5 | $0.00001 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
Grade A, and why
hush 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 10d 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
Silence Narrator Immediately
Stop all current and queued speech output immediately.
Steps
Run the following commands to kill all speech processes and clean up:
# Kill the speak daemon if running
if [ -f ~/.claude-code-narrator/daemon.pid ]; then
kill $(cat ~/.claude-code-narrator/daemon.pid) 2>/dev/null || true
rm -f ~/.claude-code-narrator/daemon.pid
fi
# Kill any running kokoro-speak.py processes
pkill -f kokoro-speak.py 2>/dev/null || true
# Remove the FIFO to clear any queued messages
rm -f ~/.claude-code-narrator/fifo
After Hushing
Narrator remains enabled after hushing -- only the current and queued speech is stopped. New hook-triggered speech will resume when Claude's next action fires a hook. The daemon will be restarted automatically by speak.sh when the next speech is enqueued.
If the user wants to disable narrator entirely (not just silence current speech), suggest using /narrator:off instead.
Inform the user: "Silenced. Narrator is still enabled and will speak on the next action."
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.
- 10d ago First seen · 35 lines · 7 tokens per session scan A 02290144032b
hush is a command published in the GitHub repository shreyas-s-rao/claude-code-narrator (26 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 270 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 2026-08-30.
Other commands, from other repositories
discover
Interview the user to capture their vision and write a Suhail-format plan that the rest of the pipeline can execute via /su:go.
init
Scan the current project and cache stack, layout, conventions, and module intel under .suhail/intel/. Required precursor for /su:go and /su:discover.
status
Print the current Suhail run's status dashboard. Read-only — never advances state.
tour
Interactive code tour - explore code flow by drilling into functions.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.