deploy-able

A deployment guide for Able Desk, a support-desk application, on the user's own Cloudflare account and domains. It treats each business deployment as separate and stores its data there.

In plain words
What is it for?
Use it to deploy Able for a business, check an unfinished deployment, configure its Cloudflare resources, or prepare it to serve customers.
Why use it?
It provides an ordered way to resume or complete setup without skipping required configuration. It also identifies the points where a person must take over.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/codeyogi911/able/deploy-able
Any agent
npx skills add codeyogi911/able --skill deploy-able
Clone the repo
git clone --depth 1 https://github.com/codeyogi911/able

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00070 $0.00857
Opus 5 $0.00035 $0.00428
Sonnet 5 $0.00014 $0.00171
Haiku 4.5 $0.00007 $0.00086

Measured yesterday against content hash f469c92d1f37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-able 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 yesterday.

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.

.claude/skills/deploy-able/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy Able for a business

You are standing up one single-tenant Able Desk deployment in the user's Cloudflare account, on their domains, holding their data. There is no hosted Able service to sign into.

docs/deployment.md is the authoritative runbook — read it before acting, and follow its steps in order. This skill is the driver: it tells you how to sequence the work, what you may do unattended, and where to stop.

Before you start

  1. Read AGENTS.local.md if it exists. It is the deployment's standing context — hostnames, which rails are on, where the deployment left off. If it does not exist, copy AGENTS.local.example.md to AGENTS.local.md and fill it in with the user as you go. Never commit it.
  2. Read docs/adopt.md for the tenant boundary. Nothing about this business goes into a tracked file.
  3. Establish where the deployment already is. A resumed deployment is the normal case — check what exists before creating anything: npx wrangler whoami, npx wrangler d1 list, npx wrangler r2 bucket list, npx wrangler secret list, and whether the Worker already serves /healthz.

Sequence

Work docs/deployment.md §1 → §8 in order. Do not skip ahead: later steps fail confusingly when an earlier gate is incomplete, and several steps are irreversible in practice once customers are pointed at them.

Announce which step you are on, what you are about to run, and what the user must do themselves. After each step, verify rather than assume — the runbook's §7 list is the acceptance criteria, not a formality.

You may do these unattended

  • npm ci, npm run check, npm run build:assets.
  • Read-only Wrangler and Cloudflare inspection to establish current state.
  • Apply committed D1 migrations (npm run db:migrate:local; npm run db:migrate:remote once the user confirms the target).
  • Generate values that should be random — for example a CUSTOMER_CAPABILITY_SECRET of at least 32 characters — and hand them to the user to set. Do not put a generated secret into a file, a commit, or your visible output beyond what the user needs to paste.
  • Draft workspace settings, knowledge articles, and email templates for the user's review.
  • Run the §7 validation checks and report results truthfully, including failures.

Read the full file on GitHub · 47 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. yesterday First seen · 47 lines · 70 tokens per session scan A f469c92d1f37

Subscribe to this mod's changes

deploy-able is a skill published in the GitHub repository codeyogi911/able (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 857 once invoked, about $0.0003 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 2026-08-31.