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/youngjaedev/my-claude-plugins/convenenpx skills add YoungjaeDev/my-claude-plugins --skill convenegit clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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/youngjaedev/my-claude-plugins/convene)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/convene"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/convene.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 5.1 | $0.00118 | $0.08356 |
| Opus 5 | $0.00059 | $0.04178 |
| Sonnet 5 | $0.00024 | $0.01671 |
| Haiku 4.5 | $0.00012 | $0.00836 |
Grade D, and why
convene scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
a failing `jq` would destroy a perfectly good set of pins and silently send the next run back to Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
DIR=$(cat ".claude/state/council-run-$RUN_KEY") How it starts
The opening of the file, as written. The whole thing — 638 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council — cross-vendor deliberation
Put one question to three models from three different vendors, make them read and rebut each other, and write down what they agreed on, what stayed contested, and what nobody could answer.
The point is divergence. Several Claude subagents share weights and therefore share their systematic mistakes; a real second opinion has to come from a model somebody else trained.
Cross-runtime interactive input
Every question below runs through a capability-aware interactive-input gate rather than one hardcoded tool:
- Claude Code: use
AskUserQuestion. - Codex: use
request_user_inputwhen that tool is exposed. When it is not, ask ONE concise blocking question only where a wrong assumption would be costly; otherwise proceed on a documented safe default and state the assumption.
This plugin is Claude-only in practice (the Claude seat needs the Agent tool), so the Claude
row is the operative one. The other row is kept so the body never asserts that a single
interactive tool exists.
Roles
The chair is the main session. It composes prompts, relays the user's answers, and synthesizes. The chair is not a seat and does not vote.
| Seat | Runner | Registry key |
|---|---|---|
| codex | codex exec |
seats.codex |
| agy | agy --print |
seats.agy |
| claude | Agent tool with a model override |
seats.claude |
Step 0 — resolve the model registry
Seat models are pinned in ~/.claude/council-models.json so they survive across repos and are
confirmed at most once a week.
The seven-day window is a constant here, never a field read back from the registry. A TTL
taken from the file it governs is not a guarantee: one hand-edited ttl_days and the pins never
come up for confirmation again, which is exactly the "always ask on expiry" property this design
was chosen for. A timestamp that is missing, non-numeric, or in the future is treated as expired
for the same reason: those are the shapes a corrupted or tampered registry takes, and none of
them should buy indefinite freshness.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -54 tokens per session 74ad8972f542
- 5d ago First seen · 638 lines · 172 tokens per session scan D aaa92b096a0b
convene is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 8,356 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent to send conversation or user data out, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…