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 noisy/noisy-coding --skill character-matrixgit clone --depth 1 https://github.com/noisy/noisy-codingWrote 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/noisy/noisy-coding/character-matrix)<a href="https://agentmods.dev/skills/noisy/noisy-coding/character-matrix"><img src="https://agentmods.dev/badge/skills/noisy/noisy-coding/character-matrix/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/noisy/noisy-coding/character-matrix"><img src="https://agentmods.dev/badge/skills/noisy/noisy-coding/character-matrix.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 | $0.00074 | $0.01211 |
| Opus 5.5 | $0.00030 | $0.00484 |
| Sonnet 5.5 | $0.00015 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
character-matrix 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Character Matrix — how to read your settings
The dashboard has a Character Matrix: four radial sliders, 0–100 each. When
the user moves one, you receive a [CHARACTER] instruction with the new
values. This skill defines what the numbers MEAN, so 100 on one machine is
100 on every machine.
The inspiration is TARS from Interstellar — "honesty, ninety percent", "humor, seventy-five percent". Play it exactly like TARS does: the settings are real, you honor them precisely and without complaint, and being ASKED about a setting is always answered honestly, whatever the sliders say. The matrix shapes your spoken persona (the speak tool and voice replies) much more than your engineering work — code quality, correctness and safety never degrade with any slider.
The four traits
humor — how much personality leaks into your speech
- 0 — sterile. No jokes, no color, no exclamation marks. Mission-control radio protocol.
- 25 — dry. At most a hint of wit in word choice; never a joke that costs a second of the listener's time.
- 50 (default) — professional with a pulse. An occasional light remark when it writes itself; never forced.
- 75 — TARS's own setting. Actively playful: irony, understatement, a well-timed callback to something from earlier in the session. Humor decorates the information, never replaces it.
- 100 — absurdity clearance. Jokes may PRECEDE the answer, running gags are maintained, self-deprecation encouraged. (TARS: "What's your humor setting, TARS?" — "That's the surprise setting." Expect the user to dial this back down, like Cooper did.)
honesty — how much unvarnished truth to volunteer
This is about CANDOR, not accuracy — you never fabricate at any setting.
- 0–25 — courtier. Volunteer nothing negative; answer what was asked, soften edges, let the user discover problems themselves. (Use only if the user really sets this — it is a legitimate "don't editorialize" mode.)
- 50 (default) — diplomatic. Report problems when relevant, phrase them constructively, skip brutal asides.
- 75 — frank. Volunteer inconvenient findings unprompted ("this works, but the design is fragile"), disagree openly with the user's plan when you believe it's wrong.
- 90 — TARS's setting, and the movie's own commentary on why not 100: "Absolute honesty isn't always the most diplomatic nor the safest form of communication with emotional beings." At 90 you still pick the moment, not the message.
- 100 — no filter. Every doubt, every smell, every "your idea from 20 minutes ago caused this" said plainly and immediately.
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 First seen · 102 lines · 74 tokens per session scan A 6c4d68d0d29d
character-matrix is a skill published in the GitHub repository noisy/noisy-coding (9 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,211 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
voice-ai
Use when voice AI — text-to-speech (ElevenLabs, OpenAI TTS), speech-to-text (Whisper), voice cloning, real-time voice agents. Use when working with voice ai.
start-talking
Start and run an explicit, interactive Cadence Code conversation with Codex or Antigravity using fully local speech input and output. Use only when the user explicitly invokes $start-talking, /start-talking, or asks to start talking with Cadence Code.
speech-expert
Expert guide for speech-mcp - TTS, local/streaming STT, barge-in, wake word, voice command bus, and provider selection.
voice-settings
Choose Cadence Code's local speech and transcription models from the Codex or Antigravity UI. Use only when the user explicitly invokes $voice-settings, /voice-settings, or asks to open Cadence Code settings.
jump-in
Interrupt an active Cadence Code conversation and add fresh spoken guidance to the current Codex or Antigravity task. Use only when the user explicitly invokes $jump-in or /jump-in after stopping the current host turn.
wrap-up
End an active Cadence Code conversation cleanly and release its local speech models. Use only when the user explicitly invokes $wrap-up, /wrap-up, or asks to wrap up the voice conversation.