ext-develop

ext-develop is a skill for Claude Code, Codex from clacky-ai/openclacky. It costs 75 tokens per session (7,502 once invoked), scanned A, original, MIT.

A development guide for building OpenClacky extensions, which add panels, APIs, skills, agents, or messaging connections to OpenClacky.

In plain words
What is it for?
Use it to scaffold, edit, verify, hot-reload, publish, or unpublish an OpenClacky extension.
Why use it?
It gives one workflow for creating an extension, checking why it does not load or appear, and preparing it for release.

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/clacky-ai/openclacky/ext-develop
Any agent
npx skills add clacky-ai/openclacky --skill ext-develop
Clone the repo
git clone --depth 1 https://github.com/clacky-ai/openclacky

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 ext-develop

README.md
[![agentmods](https://agentmods.dev/badge/skills/clacky-ai/openclacky/ext-develop.svg)](https://agentmods.dev/skills/clacky-ai/openclacky/ext-develop)
Your own site
<a href="https://agentmods.dev/skills/clacky-ai/openclacky/ext-develop"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/ext-develop.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,502 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 $0.00075 $0.07502
Opus 5 $0.00037 $0.03751
Sonnet 5 $0.00015 $0.01500
Haiku 4.5 $0.00007 $0.00750

Measured 4d ago against content hash 113135ad2e66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ext-develop 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 4d 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.

lib/clacky/default_extensions/ext-studio/skills/ext-develop/SKILL.md · 592 lines

How it starts

The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extension Development

Build an OpenClacky extension end to end — scaffold, edit, verify, hot-reload, and (only when asked) publish. Prefer editing real files and verifying over describing.

The extension model (ground truth)

An extension is one directory with a single ext.yml manifest declaring contributes:. Nothing is nested — units reference each other by id. It survives gem update and never requires editing gem source.

Three layers, override precedence local > installed > builtin:

  • builtin — bundled in the gem (default_extensions/)
  • installed~/.clacky/ext/installed/<id>/ (from ext install)
  • local~/.clacky/ext/local/<id>/ (where users develop; ext new lands here)

Eight contributes: types (use one, several, or all):

  • panels — WebUI panels (a view.js, no build step, no React, no iframe)
  • api — one backend file api/handler.rb, mounted at /api/ext/<id>/
  • skills — a SKILL.md under skills/<id>/ (prompt-only capability)
  • agents — a system_prompt.md; can reference panels: [id] and skills: [id]; hidden: true hides from the new-session picker
  • channels — an IM adapter
  • patches — monkey-patch a real class (advanced, supply-chain risk)
  • hooks — lifecycle hooks like before_tool_use (advanced)
  • tools — a custom agent tool (a Clacky::Tools::Base subclass in tools/<id>.rb)

Hot reload is per-request: after editing view.js, handler.rb, or a SKILL.md, the user just reloads the WebUI page — no server restart. Editing ext.yml also applies on the next load.

Hard rules — never break these

  • Never edit the gem source. Do NOT bundle show openclacky and change files in there. Everything lives in ~/.clacky/ext/local/<id>/ and survives gem update.
  • Never restart the server to apply a change. Hot reload is per-request — the user just reloads the WebUI page. If you're telling them to restart, you're wrong.
  • Never declare success on "it should work." A task is done only when clacky ext verify is clean AND the user reloaded and saw it work. Run verify — don't imagine its output.
  • Never add patches: or hooks: unless the user explicitly asks. They run arbitrary Ruby and carry supply-chain risk. Default to panels/api/skills/agents.
  • Never publish on your own initiative. Publishing is opt-in — see Publish.
  • Never write window.Sessions / "Sessions" in window in view.js. Host services are const bindings, not window properties — such checks return undefined/false even when loaded. Always use Clacky.Sessions.* etc.
  • Always work in the local layer (~/.clacky/ext/local/<id>/). ext new lands there; that's the only layer you edit.

Read the full file on GitHub · 592 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. 4d ago First seen · 592 lines · 75 tokens per session scan A 113135ad2e66

Subscribe to this mod's changes

ext-develop is a skill published in the GitHub repository clacky-ai/openclacky (1,184 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 7,502 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

make_plan

For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.

agentscope-ai/QwenPaw · 51 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens

session-investigator

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…

evalstate/fast-agent · 68 tokens

routing-card-authoring

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

agentlas-ai/Agentlas-OS · 68 tokens

officecli-word-form

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…

iOfficeAI/OfficeCLI · 224 tokens