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 decocms/studio --skill decocms-studiogit clone --depth 1 https://github.com/decocms/studioWrote 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/decocms/studio/decocms-studio)<a href="https://agentmods.dev/skills/decocms/studio/decocms-studio"><img src="https://agentmods.dev/badge/skills/decocms/studio/decocms-studio/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/decocms/studio/decocms-studio"><img src="https://agentmods.dev/badge/skills/decocms/studio/decocms-studio.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 | $0.00068 | $0.01383 |
| Opus 5.5 | $0.00027 | $0.00553 |
| Sonnet 5.5 | $0.00014 | $0.00277 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade C, and why
decocms-studio scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
the user before installing Bun with `curl -fsSL https://bun.com/install | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the user before installing Bun with `curl -fsSL https://bun.com/install | bash` How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate deco Studio
Every call goes through the decocms CLI, which holds the user's OAuth
session and refreshes it. The CLI is the only thing that touches the token:
call Studio with decocms api and decocms tools, and leave the session files
in the data dir alone.
Run the CLI as decocms when it is on PATH, otherwise bunx decocms@latest.
An Unknown command: tools error means a cached old version; rerun with
bunx decocms@latest.
The CLI runs on Bun, also when started with npx. If bunx is not found, ask
the user before installing Bun with curl -fsSL https://bun.com/install | bash
(Windows: powershell -c "irm bun.com/install.ps1 | iex"), then call
~/.bun/bin/bunx until a new shell has it on PATH.
1. Session
decocms auth whoami # prints Target and User when logged in
When whoami or any call says Not logged in or Could not refresh session,
give the user the decocms auth login command it prints to run in their own
terminal (it opens a browser for them to approve), wait for them, then retry.
The session refreshes itself, so this is normally needed once per machine. Do
not work around a missing session with API keys, MCP tokens or presigned URLs.
A self-hosted or local studio adds --target <url> to every command, e.g.
--target http://localhost:3000.
Done when whoami prints the user the person expects. Its Target is the
studio origin used in the links below.
2. Organization slug
Every org-scoped call needs the organization's slug, the first path segment
of a studio URL (https://studio.decocms.com/<slug>/...). List the user's
organizations and pick the one they mean; ask when several fit:
decocms orgs # slug<TAB>name per organization; --json adds ids
When the user names a project instead of an org, search across their orgs:
decocms api "/api/_me/projects/search?q=<term>" returns each match's orgSlug.
3. Builtin tools first
Tools are the main surface: the web app calls the same ones. Each tool's input schema is the documentation, so look it up instead of guessing fields.
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.
- 2d ago Changed · +27 lines scan A → C 8bbc8f37312a
- 10d ago First seen · 87 lines · 68 tokens per session scan A 0614cd6f8359
decocms-studio is a skill published in the GitHub repository decocms/studio (409 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,383 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other skills, from other repositories
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
cococonverge
CocoPivot — multi-pod convergence synthesizer. Deterministically deduplicates findings from N parallel pod outputs into one prioritized, coordinated action plan. Invoked via $pivot run/show/status/clear.
plan
Enter the Plan phase of CocoBrew. Runs CocoSpec quality gate pre-flight, reads spec.md and discuss.md (if present), invokes Coco native plan mode as a mandatory gate, captures the approved plan to plan.md, creates initial flow.json template, and commits. Must have $spec completed first.
lean-debt
CocoLean shortcut debt ledger — harvests cocoplus: comment markers across the CocoPod and produces a ranked deferral report sorted by ceiling imminence and age.
cocoplus-config
CocoPlus configuration SSOT — $cocoplus sync propagates cocoplus.toml into downstream artifacts; $cocoplus migrate-config converts legacy safety-config.json. Invoked via $cocoplus sync and $cocoplus migrate-config.