wiki

wiki is a skill for Claude Code, Codex from autonomous-ai/autonomous-workshop. It costs 385 tokens per session (2,039 once invoked), scanned A, original, Apache-2.0.

A searchable engineering knowledge base for mechanical design decisions. It stores explanations about parts such as bearings, gears, joints, linkages, and grippers, including why a design may work or fail.

In plain words
What is it for?
Use it to search, read, list, add, and check wiki pages about mechanical mechanisms and design constraints.
Why use it?
It lets an agent find previously recorded engineering guidance before making a design decision, without changing CAD geometry or other tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; $skill-name invocation.

Good fit Use it to search, read, list, add, and check wiki pages about mechanical mechanisms and design constraints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/autonomous-ai/autonomous-workshop/wiki
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 wiki
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 wiki

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/wiki"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 385 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,039 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 $0.00385 $0.02039
Opus 5.5 $0.00154 $0.00816
Sonnet 5.5 $0.00077 $0.00408
Haiku 4.5 $0.00038 $0.00204

Measured 2d ago against content hash d3465442691d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wiki 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.

src/workshop/make/skills/wiki/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design wiki

A knowledge base, not a workflow and not a gate. It holds the engineering the CAD tooling does not know: which joint to draw, what makes a shaft stiff enough, which numbers make a linkage turn, and why a correct-looking printed mechanism still does not run. It writes no geometry and changes no other skill.

W="$(workshop skills path)/wiki/scripts/wiki"   # stdlib only: python3 or .venv/bin/python
$W search <words...>                 # ranked sections, path:line, snippet
$W search spindle --pages            # one line per page; synonyms expand
$W show <slug>[#section]             # print a page or one section
$W list [--tag gear]
$W new <topic>/<slug> --title "..."  # page from the template
$W lint                              # must pass before a wiki edit is done

Inside a Workshop product run the wiki is consult-only. Its bytes are materialized read-only and bound into the run's input manifest like every other skill, so new, a page edit and a synonyms.txt edit are all refused there — and a run that tampered with them would fail its resume. Search, show and list freely; step 5 below does not apply in a run. Append a rule the wiki lacked, with its evidence, to LESSON-PROPOSALS.md at the run root; the host's Make lessons loop carries gate failures into the design vault, and the Workshop build loop writes durable rules back to this wiki upstream. Paths written skills/<name>/... in these pages name a sibling Make skill: read them under "$(workshop skills path)/<name>/". Upstream's step-to-source and stl-to-step are not Workshop skills: a reverse-engineering/ page that names them describes tooling a run does not have, and its rules stand without it. Machines and fixtures the pages cite by name live in the upstream autonomous-product-to-cad repository, not in a product run; the numbers quoted are the whole example.

The loop: search, think, design, write back

  1. Search before deciding. Whenever a part turns, slides, swings, latches, carries load or is driven, search the wiki for the joint, the element and the failure first — search shaft deflection, search keyed phase, search worm back-drive. Start a new machine at show mechanism-design, which holds the design sequence and the archetype chooser.
  2. Read the hits, not the whole wiki. Open the two or three sections the search ranks highest with show slug#section and follow their [[links]] only where the design needs them.
  3. Think with the page's numbers. Turn each rule you use into the project's parameter block and an assert (every page gives its assert). A decision you cannot write as a number or an assert is not designed yet. Record in the spec which page each archetype, fit and limit came from.
  4. Design the system in this order — archetype → shaft and joint layout → parameters → feasibility asserts → kinematics → motion checks — and do not start geometry until the asserts pass.
  5. Write back what you learned. Creating or editing any item ends here: when research, a calculation, a measurement, a gate failure, a kernel workaround or a user correction produces a rule the wiki did not have, add it before the task ends (below). When a search missed a page that exists, add the missing term to that page's aliases or to synonyms.txt.

Read the full file on GitHub · 133 lines

Files

What ships with it

60 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.

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 Changed d3465442691d
  2. 15d ago Changed · +76 tokens per session 986d71f0dfa6
  3. 16d ago First seen · 133 lines · 309 tokens per session scan A 5918488e6507

Subscribe to this mod's changes

wiki is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (21 stars, last pushed today), licensed Apache-2.0. It adds 385 tokens to every session and 2,039 once invoked, about $0.0015 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 2026-10-01.

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