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 design-vaultgit 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/design-vault)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/design-vault"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/design-vault/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/design-vault"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/design-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.00900 |
| Opus 5.5 | $0.00024 | $0.00360 |
| Sonnet 5.5 | $0.00012 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
design-vault scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Design vault
VAULT.json at the run root is a content-addressed snapshot of the game
design vault the host fetched for this phase: mechanism, anti-pattern,
rule-pattern, constraint, component, combo, and game nodes joined by typed
links (requires, conflicts-with, risks, mitigated-by, variant-of,
example-of, component, uses, member, exhibits). Every answer below
is computed from those links; nothing here is an opinion. The host refreshes
the snapshot before each Invent, Make, and Playtest phase, so its banked
evidence includes what earlier runs — yours and others' — sealed. When the
vault could not be reached for this phase there is no VAULT.json and
STAGE.json names no design_vault; design without vault leads then.
Read the host-provided leads named in STAGE.json first — they are computed
for this exact run. For anything beyond them, query the snapshot offline:
"$WORKSHOP_PYTHON" .agents/skills/design-vault/vault_tools.py resolve "ratchet dial"
"$WORKSHOP_PYTHON" .agents/skills/design-vault/vault_tools.py node mechanisms/hand-management
"$WORKSHOP_PYTHON" .agents/skills/design-vault/vault_tools.py links anti-patterns/alpha-solve --reverse --type risks
"$WORKSHOP_PYTHON" .agents/skills/design-vault/vault_tools.py guidance mechanisms/stacking-and-balancing
"$WORKSHOP_PYTHON" .agents/skills/design-vault/vault_tools.py check mechanisms/a mechanisms/b --with-constraints
resolvemaps a name to a node by exact slug, declared alias, then a conservative fuzzy match;nullmeans the vault has no such mechanism.checkreportsconflict(declaredconflicts-with),unmet-requirement(arequiresoutside the set),risk(arisksedge with the recordedmitigated-byfixes and the newest banked evidence), andcombo-risk(a recorded failure of a mechanism set whose every member is in the combination).guidancebriefs a mechanism: definition, its top risks with fixes, and exemplar games.
Rules:
- Every mechanism in an Invent concept must resolve to a vault node or be
declared under
novel_mechanismswith a definition; a combination the vault marksconflicts-withor leaves arequiresunmet is refused by the finalizer and the host. Risks are never refusals — they become Playtest leads. - A
requiresedge that points at arule-patterns/*node is met by naming that rule in the concept's optionalapplied_rule_patternslist (a slug or the fullrule-patterns/<slug>path, at most 32). Declare only rules the design actually applies; an entry that is not a rule-pattern node is refused (rule-pattern-unknown).resolve "<name>" --folder rule-patternsanswers what a rule is called. - A lead is a lead, not a verdict. Confirm or dismiss each one against the exact artifact and say why; the host banks what you confirmed and records what you dismissed in the vault for every later run.
- Never edit
VAULT.jsonor this skill; the host owns them. Propose vault changes in your stage outcome instead. - Never print or search
VAULT.jsondirectly (cat,sed,head,rg): it is one packed line of about a megabyte, so the output only floods your context and is dropped from the host's event stream. Query it throughvault_tools.pyonly.
What ships with it
1 file 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.
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 Changed · +6 lines 44d9387af2a3
- 1mo ago First seen · 56 lines · 59 tokens per session scan A 3120336e9df0
design-vault is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (21 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 900 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
pygame-core
Structure a pygame (pygame-ce) game in Python: the init/event/update/draw loop, delta-time movement, Surface/Rect blitting, keyboard/mouse input, and Sprite/Group management with collision. Use when building or debugging a pygame game — when the user mentions pygame, pygame-ce, the game loop, blit, Surface, Rect…
vibeue
Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…
demo-1-terminal-arcade
Demo skill that builds a colorful, playable terminal Snake game in a single pure-stdlib Python curses file — score HUD, speed ramp, eat/death animations, and a game-over screen.
godot-development
Godot 4 reference patterns: signal-vs-call and physics-body decision tables, resource sharing traps, input handling, a common mistakes catalog, a GDScript to C# rosetta, typed class structure, pooling, autoloads, GUT tests, and collision layer constants. Use when designing, writing, or reviewing Godot 4 code.
glyphs-mcp-development
Use this skill to create, extend, or review reusable workspace-first Glyphs Python scripts and Python plug-ins, including general, reporter, filter, palette, select-tool, and file-format plug-ins, while grounding API and template choices in the bundled Glyphs documentation.
game-ai-patterns
Game AI code patterns: behavior tree node types, FSM transition tables, utility AI consideration curves, GOAP action definitions, Godot NavMesh agent setup, and field-of-view sensing. Use when writing or reviewing NPC decision-making, pathfinding, or perception code.