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 skills add autonomous-ai/autonomous-os --skill speaker-recognizergit clone --depth 1 https://github.com/autonomous-ai/autonomous-osWrote 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/skills/autonomous-ai/autonomous-os/speaker-recognizer)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/speaker-recognizer"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/speaker-recognizer/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/skills/autonomous-ai/autonomous-os/speaker-recognizer"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/speaker-recognizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 27 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00066 | $0.01028 |
| Opus 5.5 | $0.00026 | $0.00411 |
| Sonnet 5.5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
speaker-recognizer scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
When in doubt → see `reference/enroll-flows.md`. All curl + error handling → `reference/api.md`. How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speaker Recognizer
Each mic transcript is prefixed Speaker - Name: when recognized, or Unknown Speaker: [voice:voice_N] ... (audio save[d] at <path>...) otherwise. The audio path is the WAV of whoever spoke this turn — use it (with paths from prior same-tag turns when needed) to enroll on POST /speaker/enroll.
Self-enrollment only — never enroll one person's voice under another person's name.
Entry gate
Unknown identity is metadata, not an enrollment request. Without a clear self-introduction, an explicit voice enrollment/management request, or a reply continuing a user-initiated enrollment, handle the actual request directly: no speaker API calls, no enrollment reference reads, no name question, and no replacement acknowledgment. Meaningless fragments follow the device's normal silence rules. Same-tag history alone does not start or resume enrollment; a new unrelated request takes priority.
A name counts only when the speaker identifies themselves, not when addressing the agent ("Mike, open Chrome"), mentioning another person, or appearing in metadata. Preserve any substantive request accompanying a self-introduction; enrollment must not replace it.
Decision matrix — after the entry gate
| Signals in current turn | Prior same-tag turns? | Action |
|---|---|---|
Unknown Speaker: + path + name + ≥25 words |
— | Enroll now with current path only. |
Unknown Speaker: + path + name + <25 words |
≥1 prior path same [voice:N] |
Enroll now with all same-tag paths (oldest→newest). |
Unknown Speaker: + path + name + <25 words |
none | Ask one follow-up: "say your name + ~25–30 words". |
| Explicit enrollment request + path + NO name | any | Ask for the speaker's own name; request more audio only if needed. |
| Reply continuing enrollment, still no name or insufficient audio | same enrollment | Explain what is missing once; do not loop or enroll under a guessed name. |
Speaker - <Name>: |
— | Already identified — skill not needed. |
| "who do you know?" / "list voices" | — | GET /speaker/list. |
| "forget my voice" / "remove Alex" | — | POST /speaker/remove. |
| Telegram voice note + intro | — | Convert to WAV + enroll with Telegram fields. |
| Telegram voice note + "who is this?" | — | POST /speaker/recognize. |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +5 lines · -66 tokens per session 3105f5d57574
- 1mo ago First seen · 53 lines · 132 tokens per session scan A 533bde91aa6c
speaker-recognizer is a skill published in the GitHub repository autonomous-ai/autonomous-os (378 stars, last pushed 18d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,028 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rosclaw-embodied
A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.
srdf
MoveIt2 SRDF authoring, validation, and planning-semantics workflow. Use when creating, editing, inspecting, or validating .srdf files, MoveIt planning groups, virtual joints, passive joints, end effectors, group states, disabled collisions, URDF-paired planning semantics, or SRDF handoff for live review. Use the URDF…
urdf
URDF robot description authoring and validation. Use when creating, editing, inspecting, validating, or debugging .urdf files, robot links, joints, limits, inertials, visual/collision geometry, mesh references, frame conventions, or robot-description artifacts. Use the SRDF skill for MoveIt2 semantic groups and…
step-parts
Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers, bearings, standoffs, and other catalog components. Use when Codex needs to search the hosted step.parts catalog before…
gcode
Slice 3D models into printer-ready G-code with OrcaSlicer, the open-source slicer with built-in profiles for most FDM printers (Prusa, Bambu Lab, Creality, Voron and more). Use when the user wants an .stl, .3mf or .obj model sliced for their printer, as a sliced .gcode.3mf or plain .gcode, headless with OrcaSlicer's…
evaluating-cosmos-policy
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.