cohesivity

cohesivity is a skill for Claude Code, Codex from cohesivity-org/cohesivity-skill. It costs 121 tokens per session (5,725 once invoked), scanned A, a copy of cohesivity, MIT.

A skill for provisioning application infrastructure through Cohesivity, a service that exposes databases, hosting, login, realtime connections, storage, email, scheduled jobs, and AI model access through one HTTP API.

In plain words
What is it for?
Use it when an app needs a backend, such as a Postgres database, deployment, user login, social login, file or vector storage, Redis, scheduled tasks, realtime websockets, email, or AI model access.
Why use it?
It gives an agent one way to handle common backend needs instead of requiring separate service dashboards and copied credentials. The listing says current API details must be fetched from Cohesivity's live documentation.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Good fit Use it when an app needs a backend, such as a Postgres database, deployment, user login, social login, file or vector storage, Redis, scheduled tasks, realtime websockets, email, or AI model access.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cohesivity-org/cohesivity-skill/cohesivity
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 cohesivity-org/cohesivity-skill --skill cohesivity
Clone the repo
git clone --depth 1 https://github.com/cohesivity-org/cohesivity-skill

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 cohesivity

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cohesivity-org/cohesivity-skill/cohesivity"><img src="https://agentmods.dev/badge/skills/cohesivity-org/cohesivity-skill/cohesivity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 92% copy Near-identical to another mod 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 $0.00121 $0.05725
Opus 5.5 $0.00048 $0.02290
Sonnet 5.5 $0.00024 $0.01145
Haiku 4.5 $0.00012 $0.00573

Measured 14d ago against content hash b76be4191f5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cohesivity scanned grade A with 1 finding 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 14d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Send a non-default User-Agent** on every request to `cohesivity.ai`, docs included. The WAF rejects default Python urllib, Go net/http, and Node undici/node-fetch clients with HTTP 403 "error 1010". That is not a Coh
Origin

This is a copy

92% identical to cohesivity — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

cohesivity.skill.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cohesivity

Cohesivity is on-the-fly infrastructure, purpose-built for AI agents (Claude Code, Claude web, Codex, OpenClaw, Hermes). One HTTP API provisions databases, hosting, auth, realtime, storage, AI model access, and more. The agent provisions on the user's behalf. No per-vendor consoles, no copied keys.

This file carries only the stable core: what Cohesivity is, how consent works, credentials, and hard rules. Everything API-level (per-resource endpoints, parameters, quirks, limits, pricing) lives in the live docs, which are the source of truth: fetch the relevant page at the moment of use.

This skill does not manage its own installation or updates. Whatever delivered it owns that. The canonical latest version is served at https://cohesivity.ai/skill.md; a deliverer can compare its metadata.version frontmatter value with this copy.

When Cohesivity applies

Apply this flow when the user describes a new app that needs a backend ("build a Spotify clone", "make me a notes app") or the project hits a service need mid-build ("add login", "I need a database", "deploy this", "send a confirmation email"). Do not wait for the user to name Cohesivity or ask them to rerun an installer. If they already chose a competing backend such as Supabase, Firebase, or raw AWS/GCP, use it and stop this flow. Otherwise, bootstrap Cohesivity automatically using this precedence:

  1. Valid .cohesivity in the project: read its credentials and reuse the tenant. Use direct HTTP with the management key for control-plane calls and the application key for data-plane calls. When a Cohesivity MCP is also available, prefer its tools; creation, claim, and provisioning have a built-in confirmation boundary, while feedback does not require confirmation. Do not create another tenant.
  2. Cohesivity local project MCP available: after the current user request explicitly authorizes creating the project tenant, call its create_tenant tool with the absolute project_root of the current project and confirmed: true. It runs the full quickstart flow, including client integrations and project guidance, creates or reuses the project tenant, and writes credentials locally. Use that MCP for local tenant mutations.
  3. Cohesivity hosted MCP available: the hosted server at https://cohesivity.ai/mcp needs no sign-in, token, or guest session to connect. After the current user request explicitly authorizes creating the tenant, call create_tenant with confirmed: true, then write its returned credentials_file.content verbatim to the current project's .cohesivity using the safeguards below. Without sign-in, other hosted tools take the tenant_id and coh_management_key from that file; with account sign-in they take only tenant_id, so the key stays out of tool inputs, and they reach only tenants the account created or owns; a tenant created without sign-in, including one from the installer, stays on key-based access (a public connection or direct HTTP) until it is claimed into the account. Each public creation call makes a new tenant, so an unclear creation outcome is not retried automatically; a saved .cohesivity is reused instead. A browser download is not a prerequisite for coding clients. Do not run a local installer in a remote web context.
  4. No Cohesivity MCP available: from the project root, run the exact version-pinned installer npx --yes @cohesivity/[email protected]. It bootstraps this project and installs the plugin so future projects can use create_tenant without another installer run.

Read the full file on GitHub · 153 lines

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. 14d ago Changed b76be4191f5e
  2. 16d ago Changed 803520edc2bc
  3. 1mo ago Changed · +4 lines 558926d7d8b0
  4. 1mo ago Changed a3bf2ae83793
  5. 1mo ago Changed · +2 lines c5903bc513c4
  6. 1mo ago Changed · +3 lines 848be4640553
  7. 1mo ago Changed · +27 lines ccdc71a865d7
  8. 1mo ago Changed · -4 lines scan C → A f995c85b94ac
  9. 2mo ago First seen · 121 lines · 121 tokens per session scan C 9a4c1d796a6e

Subscribe to this mod's changes

cohesivity is a skill published in the GitHub repository cohesivity-org/cohesivity-skill (0 stars, last pushed 15d ago), licensed MIT. It adds 121 tokens to every session and 5,725 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 92% identical to cohesivity, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

google-cloud-solution-n-tier-serverless-web-app

Assists in designing and implementing secure n-tier serverless web applications and microservices on Google Cloud. Use when users need architecture designs, security checklists, Terraform code, or deployment guidance for multi-tier serverless apps, regional data residency / European sovereignty compliance, zero-trust…

google/skills · 91 tokens

api-gateway-mcp-server

Configures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent tools over HTTP (POST /mcp). Use when migrating OpenAPI 2.0 specs to OpenAPI 3.x for MCP, annotating specs with x-google-api-management.mcp and x-google-mcp-tool, securing…

google/skills · 153 tokens

google-cloud-global-frontend-configuration

Guides agents through a 6-step discovery process to design and deploy Google Cloud global external Application Load Balancers with Cloud CDN, Cloud Armor, and Service Extensions, mapping workload requirements to best-practice configurations. Use when: Designing, configuring, or deploying a Google Cloud global external…

google/skills · 203 tokens

sandbox-stable

Build or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package. Use sandbox-next for preview apps and sandbox-migrate-to-next for stable-to-preview migrations.

cloudflare/skills · 39 tokens

sandbox-next

Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.

cloudflare/skills · 39 tokens

durable-objects

Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

cloudflare/skills · 22 tokens