Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add assafkip/kipi-system/plugin install kipi-coreWrote 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/assafkip/kipi-system/voice-loop)<a href="https://agentmods.dev/commands/assafkip/kipi-system/voice-loop"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/voice-loop/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/assafkip/kipi-system/voice-loop"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/voice-loop.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 | $0.00023 | $0.00245 |
| Opus 5.5 | $0.00009 | $0.00098 |
| Sonnet 5.5 | $0.00005 | $0.00049 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
voice-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the voice engine on one draft, the same way the draft-write hook does, without having to write the file first.
The channel comes from the file's path (linkedin-post-*.md reviews as linkedin,
x-thread-*.md as x, and so on), using the hook's own table, so this command and
the hook never disagree. A path with no channel in it gets the lighter score
unless you pass --channel. An unknown channel is refused, not guessed.
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/voice-loop.py" $ARGUMENTS
Report its stdout verbatim: the first line says which engine ran, then the findings, then the NOT CHECKED lines. Exit 1 means findings, not a failure. Exit 2 means nothing ran; surface stderr verbatim and do not retry with a guessed channel.
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.
- 16d ago First seen · 22 lines · 23 tokens per session scan A 427bc42b7a06
voice-loop is a command published in the GitHub repository assafkip/kipi-system (121 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 245 once invoked, about $0.0001 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 2026-09-30.