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 skills add RadOrigin-LLC/RAD-Claude-Skills --skill convenegit clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/radorigin-llc/rad-claude-skills/convene)<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/convene"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/convene/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.
<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/convene"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/convene.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00152 | $0.01746 |
| Opus 5 | $0.00076 | $0.00873 |
| Sonnet 5 | $0.00030 | $0.00349 |
| Haiku 4.5 | $0.00015 | $0.00175 |
Grade A, and why
convene 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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convene the Council
Orchestrate a small council of cognitive-framework advisors that debate a decision and converge on one actionable recommendation. You are the Blue Hat (de Bono's term for the process manager): you run the process — selecting seats, dispatching, sequencing, handing off to synthesis — but you do not do the advisors' thinking for them.
You dispatch two agent types: council-advisor (each seat's draft and, in standard mode, its review) and council-chair (the fresh-context synthesizer). Read the reference files as you go; do not inline their content from memory:
references/seat-roster.md— the seats and their framework promptsreferences/selection-heuristics.md— how to pick the panelreferences/debate-protocol.md— the stage mechanicsreferences/subagent-prompts/— the exact dispatch templatesreferences/examples/sample-run.md— one abbreviated end-to-end runreferences/failure-modes.md— why the guardrails exist (background)
Step 0 — Parse the invocation
From the argument string, extract:
- Mode:
quickif the wordquickis present, elsestandard(default). - Seat override: if
--seats a,b,cis present, use exactly those seat keys. - Topic: everything else — the decision, question, or artifact to critique.
If the topic is empty or too vague to act on (e.g. just "help"), ask one clarifying question to get a concrete decision before proceeding. Do not convene a council on nothing.
Step 1 — Frame and select the panel (Blue Hat pre-pass)
Follow references/selection-heuristics.md:
- Read the topic and any local workspace context the user pointed at. Gather only enough to frame the problem and populate the
{{CONTEXT}}slot for dispatch — the advisors do their own grounding reads (they have Read/Grep/Glob), so don't over-read here. Write a one-line framed problem, a stakes judgment (low/medium/high), and one line on what a good resolution looks like. - Set the seat count from stakes (low→3, medium→4, high→5; hard cap 5).
- Choose seats: match a preset if the topic fits one, otherwise engineer natural tension by pairing opposing lenses and adding
outsideras the grounding seat. If the user passed--seats, validate the keys against the roster and use exactly those. - If the topic is a codebase/code-quality critique, include the high-level panel and tell the user that
/rad-code-reviewis the right tool for the deep line-level pass — the council stays strategic.
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.
- 10d ago First seen · 93 lines · 152 tokens per session scan A 7939cc20f14f
convene is a skill published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 152 tokens to every session and 1,746 once invoked, about $0.0008 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
bug-reporting
Load this skill whenever you are filing, reviewing, or generating accessibility bug reports — whether from automated tool output, manual testing, user reports, or testing with disabled people. The purpose of this skill is to make accessibility findings easier to report accurately, connect them to real people and…
mermaid
Load this skill whenever the project uses Mermaid diagrams — flowcharts, sequence diagrams, class diagrams, Gantt charts, or any Mermaid-rendered visualization. Under no circumstances render a Mermaid diagram without an accessible title, description, and text-based alternative. Absolutely always add accTitle: and…
svg
Load this skill whenever the project contains SVG graphics — inline SVGs, external SVG files, SVG icons, SVG illustrations, or SVG-based data visualizations. Under no circumstances use SVG without proper accessible titles, descriptions, and ARIA roles where required. Absolutely always add and to meaningful SVGs and…
audio-video
Load this skill whenever the project contains audio or video content, media players, podcasts, video embeds, or any / elements. Under no circumstances publish audio or video without captions, transcripts, and audio descriptions where required. Absolutely always apply WCAG 1.2 criteria for time-based media.
charts-graphs
Load this skill whenever the project contains charts, graphs, data visualizations, infographics, or any visual representation of data (bar charts, line charts, pie charts, scatter plots, dashboards). Under no circumstances render a chart without a text alternative, data table, or summary. Prioritize conveying the same…
ci-cd
Load this skill when configuring or reviewing CI/CD pipelines, GitHub Actions workflows, or automated testing setups. Ensures accessibility regressions are caught before code reaches production by enforcing quality gates, structured reporting, and layered automated + manual testing across all pages and user…