Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/directus/monospace-agent-skillsnpx agentmods add skills/directus/monospace-agent-skills/monospaceWrote 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/directus/monospace-agent-skills/monospace)<a href="https://agentmods.dev/skills/directus/monospace-agent-skills/monospace"><img src="https://agentmods.dev/badge/skills/directus/monospace-agent-skills/monospace/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/directus/monospace-agent-skills/monospace"><img src="https://agentmods.dev/badge/skills/directus/monospace-agent-skills/monospace.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 | $0.00054 | $0.01980 |
| Opus 5.5 | $0.00022 | $0.00792 |
| Sonnet 5.5 | $0.00011 | $0.00396 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
monospace 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monospace
Work with a Monospace instance: query and mutate data through the REST API or the typed SDK, generate instance-specific types, bootstrap workspaces and discover schema, and use the per-workspace MCP server. Read the traps below, then load the reference that matches the task.
Verified against engine source 4f6f48c (reports 0.7.0) with @monospace/sdk 0.8.0 and @monospace/cli 0.1.0 from continuous build 31d52d0. Monospace is in early access. If an instance behaves differently, trust the instance and its error messages.
Principles
- Don't guess the API. Monospace has a different API and SDK from Directus. The sources of truth are the types generated from the instance (
monospace sdk generate), the instance's own responses and error messages, and these references. The workspace OpenAPI document describes item routes (use it for payload shapes and codegen). It is not a complete or fully correct catalog of management and schema routes, so use bootstrap-and-schema.md for those. - Generate types, then write against them. Examples here use illustrative collection and field names, so adapt names and types to the generated schema.
- Inspect, write, verify. Read the schema and existing rows before writing. Send an explicit
fieldsselection on item reads and writes. Afterwards, read back using the same key or the user's exact filter. - Recover, don't loop. Read the error body, including its nested
sourcechain. After 2–3 failed attempts, re-check the schema, permissions, and license instead of retrying.
Critical traps
- Envelopes depend on the endpoint. Item and most management responses are
{ data }(plusmetawhen requested). JSON login,/api/system/info, the/schemamanifest, and OpenAPI are bare. A raw itemPOSTreturns adataarray even for one object. The SDK unwraps only the top level. Nested to-many relations stayrelation.data, and to-one relations are direct. - Deletes need a selection. Use
deleteOne({ key, fields: ['id'] })/deleteMany({ filter, fields: ['id'] })/DELETE …?fields=id. Without one, the engine returns 422 and the row remains. Confirm with a read-back. - SDK call shape:
method(parameters, options?). The first argument is an object ({ key, data, fields, include, filter, sort, limit, offset, meta }), never a positional id. The optional second argument is{ unwrapEnvelope: false }, needed to keepmeta.totalCount. Collections are cased as named (client.Articles). fieldsselects scalars,includeselects relations. Example:fields: ['id'], include: { author: { fields: ['name'] } }. Don't use dotted paths, nested objects infields, ordeep. Insideinclude, arguments arefilter/sort/limit/offset(no underscore), and operators keep underscores (_eq).- Filters use underscore operators (
_eq,_in,_null), combined with_and/_or/_not, and_some/_every/_noneon to-many relations. The full operator table is in the REST reference._nullworks only on nullable fields. Field and connector capabilities decide what is filterable, sortable, and writable. - Sort uses the object form
sort: [{ field: { direction: 'desc' } }].-fieldis rejected. - No
search, nopageor cursor, no aggregates. Uselimit(default 100) +offset+ a stable sort, andmetafortotalCount. Unknown parameters can be silently ignored with a 200, so a success status doesn't prove a parameter was applied. - 64-bit integers are strings on output. Input accepts
string | number, but values outside the safe integer range can round before transmission, so pass large integers as strings. Decimals are strings too. Don't convert money through floats. - Built-in SDK transport errors: only 401 (
MonospaceAuthError) and 403 (MonospacePermissionError) get subclasses. Validation failures (400/422), 402 license limits, and 404s arrive as baseMonospaceError, so branch on.status.MonospaceValidationErroris not currently thrown. - One credential per request. A bearer token plus a stale session cookie returns 400. API keys act as their subject user, with no per-key scope. Creating another key for the same user doesn't change what it can do.
- Check the license before designing access control. The keyless Starter profile allows 0 custom roles, 0 custom policies, 0 service accounts, and 1 workspace (402 otherwise). Client-side filtering with administrator credentials is not tenant isolation.
What ships with it
7 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.
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 · -20 lines · -88 tokens per session 91405659c40b
- 1mo ago Changed · +2 lines b125330c11d0
- 2mo ago First seen · 91 lines · 142 tokens per session scan A 8beec0aebd6b
monospace is a skill published in the GitHub repository directus/monospace-agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,980 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 2026-08-31.
Other skills, from other repositories
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…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
api-design
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…