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 SoliEstre/EstreGenesis --skill roundnextgit 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/roundnext)<a href="https://agentmods.dev/skills/soliestre/estregenesis/roundnext"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/roundnext.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 | $0.00088 | $0.01108 |
| Opus 5 | $0.00044 | $0.00554 |
| Sonnet 5 | $0.00018 | $0.00222 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
roundnext 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 7d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/roundnext — one planned/blocked/new-work round
Mechanizes the composition of Constellation §13.16.6 element 5 (planned-queue scan), §13.20 (blocker tracking + nudge), and §13.18 (autonomous execution) into a single invocable round. The output of a round is: work started, queues re-sorted, blockers acted on, new work registered, and human-gated items routed to the decisions panel — never a silent "nothing to do".
Procedure (5 steps, in order)
0. Load board truth — read the live board state (board_state_get MCP tool, or the board's state.json directly). You need: planned[] (with blocked/blockReason/when), current, decisions[] (open ones), and recent done[] for context.
1. Ripeness check on unblocked planned items — for each planned item that is not blocked, ask: has its start condition arrived? (when reached, predecessor in done[], ordering satisfied, no fresher priority above it.) If ripe → start it now (§13.18: a defined-next-step proceeds without asking). When the started item is a multi-stage track (3+ phases, or spanning sessions/external waits), register it on current[] with a stages timeline (§13.31.4 — {label, status: 'pending'|'active'|'done'}); this start step is the schema's natural entry hook. If not ripe, record why in one line (this becomes the priority rationale in step 2's sort).
2. Blocker re-examination on blocked planned items — for each blocked: true item, re-verify the blocker now (don't trust the recorded blockReason — blockers go stale silently: the external dependency may have shipped, the gate may have been decided, the precondition may have been met by unrelated work). If the blocker is gone → flip to unblocked; if it is also ripe, start it; otherwise merge into the priority sort. If still blocked, keep it and pass to step 3.
3. Derive unblocking work for still-blocked items — per §13.20: for each surviving blocker, ask what would it take to clear this, and which part of that can be done from here, now? (e.g. evidence the other side is waiting for, a prerequisite refactor, a reproduction, a nudge message per the §13.20 BlockerNudge cadence). Anything actionable becomes a new planned item (priority-sorted) — or starts immediately if it is small and ripe. If nothing is actionable from this side, ensure the blocker is visible on the board (BlockerManifest) and nudge cadence is armed.
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.
- 7d ago First seen · 29 lines · 88 tokens per session scan A ebd35fe7b52a
roundnext is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 1,108 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 2026-08-31.
Other skills, from other repositories
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.
threads
List and navigate watercooler threads. Use to see active discussions, find specific threads, or get an overview of project threads.
spec-builder
Create, evolve, and archive spec-driven workflow artifacts (proposals, outcome specs, task plans). Use when work needs a durable outcome contract before execution — new deliverables or outcome changes, API/contract changes, migrations, security/privacy-sensitive work, or any long-running task where the outcome must be…
specflo-shelve
Use when the user signals they want to set the active specflo project aside ("we're done with this", "drop this", "not worth it", "shelve it", "park this for now") — map that to specflo shelve — or to pick a paused project back up ("let's pick that back up", "resume that", "un-shelve it") — map that to specflo resume.…
flowai-live-dashboard-template
Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity sparklines, and a top-contributors panel, all in a single self-contained HTML file with light/dark theming, hoverable…
agent-swarm
Agent skill for swarm - invoke with $agent-swarm.