character-matrix

A guide to the four personality controls in the noisy-coding dashboard: humor, honesty, brevity, and chatty. It explains how the 0–100 settings affect spoken replies and how character instructions should be interpreted.

In plain words
What is it for?
Use it when a character setting arrives, when speaking through noisy-coding, or when explaining or tuning the dashboard’s personality controls.
Why use it?
It gives consistent meaning to the dashboard settings across machines. It also separates conversational style from engineering quality, so changing the sliders does not lower code standards.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/noisy/noisy-coding/character-matrix
Any agent
npx skills add noisy/noisy-coding --skill character-matrix
Clone the repo
git clone --depth 1 https://github.com/noisy/noisy-coding

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.01211
Opus 5 $0.00037 $0.00606
Sonnet 5 $0.00015 $0.00242
Haiku 4.5 $0.00007 $0.00121

Measured 2d ago against content hash 6c4d68d0d29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

skills/character-matrix/SKILL.md · 102 lines

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.

Read the full file on GitHub · 102 lines

Changes

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.

  1. 2d ago First seen · 102 lines · 74 tokens per session scan A 6c4d68d0d29d

Subscribe to this mod's changes

character-matrix is a skill published in the GitHub repository noisy/noisy-coding (6 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,211 once invoked, about $0.0004 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.