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 agentmods add skills/codeyogi911/able/deploy-ablenpx skills add codeyogi911/able --skill deploy-ablegit clone --depth 1 https://github.com/codeyogi911/ableWhat 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 | $0.00070 | $0.00857 |
| Opus 5 | $0.00035 | $0.00428 |
| Sonnet 5 | $0.00014 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00086 |
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.
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
- Read
AGENTS.local.mdif it exists. It is the deployment's standing context — hostnames, which rails are on, where the deployment left off. If it does not exist, copyAGENTS.local.example.mdtoAGENTS.local.mdand fill it in with the user as you go. Never commit it. - Read
docs/adopt.mdfor the tenant boundary. Nothing about this business goes into a tracked file. - 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:remoteonce the user confirms the target). - Generate values that should be random — for example a
CUSTOMER_CAPABILITY_SECRETof 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.
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.
- yesterday First seen · 47 lines · 70 tokens per session scan A f469c92d1f37
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.
Other skills, from other repositories
odoo-data-ops
Expertise required to safely query and modify Odoo business data while maintaining a rigorous audit trail and reversibility context.
odoo-dev
MANDATORY for customizations. High-level technical expertise in Odoo's customization engine, covering Server Actions, Automated Rules, and Odoo Studio modifications.
odoo-introspector
MANDATORY for technical discovery. Expertise in Odoo's internal ORM structures, field types, and metadata interpretation.
odoo-inventory
MANDATORY for Transfers (stock.picking), Stock Moves (stock.move), and Locations (stock.location). Expertise in Odoo's logistics and warehouse structure.
odoo-get-started
MANDATORY FIRST STEP. Orientation skill to establish the Odoo World Map context (Version, Apps, Company, Permissions) BEFORE executing any other tools.
odoo-attendance
Functional expertise in Odoo's Attendance module, covering check-in/out logs, working hour verification, and overtime management.