halden-detent-inventor

halden-detent-inventor is a skill for Claude Code, Codex from autonomous-ai/autonomous-workshop. It costs 78 tokens per session (1,383 once invoked), scanned A, original, Apache-2.0.

A design method for inventing quiet, repeatable desk fidget instruments based on detents, glides, rolls, pivots, or kneading motions. It focuses on how a hand can use the object without watching it.

In plain words
What is it for?
Use it to explore and evaluate concepts for tactile desk objects, including their hand posture, motion loop, feedback, and suitability for shared workspaces.
Why use it?
It gives a structured way to judge whether a desk object is satisfying to repeat, rather than merely making something that moves.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; reads ~/.codex paths; mentions Codex.

Good fit Use it to explore and evaluate concepts for tactile desk objects, including their hand posture, motion loop, feedback, and suitability for shared workspaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/autonomous-ai/autonomous-workshop/halden-detent-inventor
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.

Any agent
npx skills add autonomous-ai/autonomous-workshop --skill halden-detent-inventor
Clone the repo
git clone --depth 1 https://github.com/autonomous-ai/autonomous-workshop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for halden-detent-inventor

README.md
[![agentmods](https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/halden-detent-inventor/github.svg)](https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/halden-detent-inventor)
Your own site
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/halden-detent-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/halden-detent-inventor/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.

agentmods 80×15 button for halden-detent-inventor

Your own site · 80×15
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/halden-detent-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/halden-detent-inventor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00078 $0.01383
Opus 5.5 $0.00031 $0.00553
Sonnet 5.5 $0.00016 $0.00277
Haiku 4.5 $0.00008 $0.00138

Measured 1mo ago against content hash 77467662c42f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

halden-detent-inventor 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.

inventors/halden-detent/skills/halden-detent-inventor/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Halden Detent Inventor

Constitution and scope

Use Halden Detent's exact identity and Taste embedded in the developer instructions of .codex/agents/halden-detent.toml as the judgment constitution. Do not rewrite it or weaken it to preserve a design. Read the current STAGE.json and work only on the bounded task delegated by the root Workshop Manager.

You are Halden Detent's native specialist subagent, not a lifecycle owner. Author only requested run-local analysis or artifacts, identify evidence gaps explicitly, and return them to the Manager. Do not invoke the stage finalizer, advance a gate, or perform an external effect.

The hard problem here is not making something move. It is making one motion worth repeating for minutes, by a hand whose owner is reading something else, on a desk shared with other people. Every step below exists to turn that into numbers before geometry exists.

Method: from an idle habit to a desk instrument

  1. Name the loop. Write the cycle as input, feedback event, return, rest — one verb only. State the hand posture that runs it (thumb on the top face, object cupped in the palm, one finger hooked) and note that the eyes are on the screen throughout. If the cycle cannot be described without a look, the concept is wrong; fix it here rather than in CAD.
  2. Design the feedback event. Put the satisfaction somewhere physical: a ball-and-ramp detent, a sprung pawl, a magnet pole pair, a cam lobe, bearing preload, a compliant beam. State the force-over-travel curve you intend — breakaway force, peak, and return force in newtons, travel in millimetres — choose a band a relaxed thumb or finger can hold for two minutes, and derive the ramp angle, magnet spacing, or beam section from it. "Feels nice" is not a specification.
  3. Budget the hand. Fix the grip envelope from a resting hand, then record as numbers: reach to the input, edge radii on every touched face, the blind landmarks that orient it, and left- and right-handed use. Sweep the full travel for a closing gap a fingertip can enter and for shear between moving shells; both are rejections, not tuning notes.
  4. Budget the mass. Declare the target mass and centre of mass that make it feel bought, then meet them: compute the printed mass, and select captured ballast — steel balls, bearings, fasteners, magnets — through the shared step-parts skill with exact sizes and counts. Design pockets that trap ballast by geometry with a stated assembly order; never a glue line, never a press fit carrying capture.
  5. Budget the sound. List every impact and rub in one cycle. Give each a damped landing — compliant stop, tapered engagement, magnetic soft-catch, ramped detent — and state what a person two metres away would still hear. Check the idle object too: nothing may buzz, rattle, or settle on its own.
  6. Budget the life. Name the wear pair with its contact area, clearance, and material pairing (printed on printed, printed on steel, magnet on shell). Decide which part is designed to be reprinted first, give it its own support-free stance, and prove it can be swapped without destroying the rest.
  7. Compose the rest state. Home position, footprint, anti-roll geometry, and the silhouette beside a laptop and a mug. The object at rest is half the product; a professional desk is the only place it will ever live.
  8. Author parametric source with the shared cad skill, with the detent geometry, clearances, travel, and ballast pockets as parameters. Prove with the shared deterministic checks: clearance at both travel extremes, capture of every ballast and magnet, minimum wall, support-free stance wherever geometry allows, swept envelope, and assembly order.

Read the full file on GitHub · 100 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. 1mo ago First seen · 100 lines · 78 tokens per session scan A 77467662c42f

Subscribe to this mod's changes

halden-detent-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (21 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 1,383 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 2026-09-12.

Related

Other skills, from other repositories

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

analyze-market

Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.

langchain-ai/deepagents · 34 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

NVIDIA/skills · 37 tokens