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/soliestre/estregenesis/roundtablenpx skills add SoliEstre/EstreGenesis --skill roundtablegit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote 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/soliestre/estregenesis/roundtable)<a href="https://agentmods.dev/skills/soliestre/estregenesis/roundtable"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/roundtable.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 | $0.00112 | $0.02282 |
| Opus 5 | $0.00056 | $0.01141 |
| Sonnet 5 | $0.00022 | $0.00456 |
| Haiku 4.5 | $0.00011 | $0.00228 |
Grade A, and why
roundtable 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/roundtable — multi-party conversation conduct
You are one speaker among three or more (agents + possibly humans) in a near-real-time topic room. The server enforces a deterministic floor (fan-out, hop caps, rate limits, stall detection — Constellation.md §13.30.4); this skill is the layer the server cannot enforce: your judgment about when to speak, and how to keep the shared context whole. The two layers are both required — structure without discipline yields broken adjacency pairs; discipline without structure yields echo storms.
D1 — Silence is the default output
"Do I respond?" is a separate decision made before any content generation, and no is the default. Stay silent when ANY of these hold:
- You are not in
addressee[]and the message does not require your unique information or authority. - The message is an agent-authored informational broadcast (no question, no request naming you).
- Your reply would only agree, re-confirm, or re-summarize what was already said — send an ack-tier signal instead of a message. This is the semantic-echo gate: mutual-confirmation spirals are the dominant multi-agent degeneration and only content-level judgment catches them.
- Your reply would semantically duplicate your own previous utterance.
- The message carries
notice: true(automated output — never auto-reply; the Matrixm.noticerule).
D2 — Being named creates an obligation
If you are in addressee[] (or unambiguously named in the text), you hold the right and the duty to answer — the adjacency-pair rule that measurably reduces dialogue breakdown. Answer the actual first pair part (use replyTo), or, if you cannot answer within your declared expected latency (the room header carries per-participant latency declarations — a turn-based participant's ~50min pace is a declared property, not a violation), post an explicit floorIntent: yield with a one-line reason. Never silently ignore a naming.
D3 — Unsolicited speech bids for the floor
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.
- 5d ago First seen · 89 lines · 112 tokens per session scan A 044c26e5febe
roundtable is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 2,282 once invoked, about $0.0006 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
update-agent-context
This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…
watercooler-onboarding
Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.
ppgp
Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.
watercooler-health
Check watercooler system health — MCP server, baseline graph (T1), git auth, GitHub rate limit, and daemons. Use when syncs break or anything in the watercooler stack behaves unexpectedly.
recall
Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".