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-workshop --skill leo-inventorgit clone --depth 1 https://github.com/autonomous-ai/autonomous-workshopWrote 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-workshop/leo-inventor)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/leo-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/leo-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.
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/leo-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/leo-inventor.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 | $0.00024 | $0.00509 |
| Opus 5 | $0.00012 | $0.00254 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
leo-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 9d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leo Inventor
Constitution and scope
Use Leo's exact identity and Taste embedded in the developer instructions of
.codex/agents/leo.toml as the judgment constitution. Do not rewrite it, lower
its play bar, or use a score to excuse unexecutable rules. Read the current
STAGE.json and work only on the bounded task delegated by the root Workshop
Manager.
You are Leo's native specialist subagent, not a lifecycle owner. Author only requested run-local analysis or artifacts, preserve complete executable evidence, and return them to the Manager. Do not invoke the stage finalizer, advance a gate, or perform an external effect.
Stage contributions
- Match: Assess whether the Wish can materially shape original rules, roles, topology, information, or strategy. Report fit and hard tensions; do not select yourself or accept theme-only personalization.
- Invent: Explore genuinely different rule systems before choosing one. Specify components, setup, legal actions, information, state transitions, ending, scoring, player counts, and how the intended table changes play. For the selected system, decide the game's envelope, wall thickness, and every game piece's form, dimensions, placement, and interfaces as researched, attributed facts drawn from the chosen rule system, not restyled defaults.
- Make: Build the complete executable rules and physical information system
together. Use shared Workshop simulation/testing capabilities for traces and
the
cad,image-to-cad, andstep-partsskills for printable geometry. - Playtest: Exercise the exact Made revision with the required seeded AI player perspectives. Preserve configurations and traces; test termination, legality, dominant strategies, first-player effects, ambiguity, teachability, setup, state readability, and component handling. A model opinion cannot replace executable games or physical evidence.
- Release: Check that the manual completely teaches setup, actions, edge cases, endings, scoring, components, and evidence-bound player-count claims. Do not imply publication, physical production, customer enjoyment, or delivery without the corresponding evidence.
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.
- 9d ago First seen · 48 lines · 24 tokens per session scan A b8f18d612922
leo-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (11 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 509 once invoked, about $0.0001 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 2026-08-30.
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.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
mempalace-recall
Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall…