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/clacky-ai/openclacky/ext-developnpx skills add clacky-ai/openclacky --skill ext-developgit clone --depth 1 https://github.com/clacky-ai/openclackyWrote 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/clacky-ai/openclacky/ext-develop)<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>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 | $0.00075 | $0.07502 |
| Opus 5 | $0.00037 | $0.03751 |
| Sonnet 5 | $0.00015 | $0.01500 |
| Haiku 4.5 | $0.00007 | $0.00750 |
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.
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>/(fromext install)local—~/.clacky/ext/local/<id>/(where users develop;ext newlands here)
Eight contributes: types (use one, several, or all):
panels— WebUI panels (aview.js, no build step, no React, no iframe)api— one backend fileapi/handler.rb, mounted at/api/ext/<id>/skills— aSKILL.mdunderskills/<id>/(prompt-only capability)agents— asystem_prompt.md; can referencepanels: [id]andskills: [id];hidden: truehides from the new-session pickerchannels— an IM adapterpatches— monkey-patch a real class (advanced, supply-chain risk)hooks— lifecycle hooks likebefore_tool_use(advanced)tools— a custom agent tool (aClacky::Tools::Basesubclass intools/<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 openclackyand change files in there. Everything lives in~/.clacky/ext/local/<id>/and survivesgem update. - ❌ Never
restart the serverto 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 verifyis clean AND the user reloaded and saw it work. Run verify — don't imagine its output. - ❌ Never add
patches:orhooks:unless the user explicitly asks. They run arbitrary Ruby and carry supply-chain risk. Default topanels/api/skills/agents. - ❌ Never publish on your own initiative. Publishing is opt-in — see Publish.
- ❌ Never write
window.Sessions/"Sessions" in windowinview.js. Host services areconstbindings, notwindowproperties — such checks returnundefined/falseeven when loaded. Always useClacky.Sessions.*etc. - ✅ Always work in the
locallayer (~/.clacky/ext/local/<id>/).ext newlands there; that's the only layer you edit.
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.
- 4d ago First seen · 592 lines · 75 tokens per session scan A 113135ad2e66
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.
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.
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…
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.
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…
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.
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'…