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 eg-upgradegit 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/eg-upgrade)<a href="https://agentmods.dev/skills/soliestre/estregenesis/eg-upgrade"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/eg-upgrade/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/soliestre/estregenesis/eg-upgrade"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/eg-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.00953 |
| Opus 5 | $0.00048 | $0.00477 |
| Sonnet 5 | $0.00019 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
eg-upgrade 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/eg-upgrade (/egup) — bring seed + plugins + skills up to date
Mode M2 (the seed's Migration B) plus the plugin/skill layer the seed does not cover.
0. Read the marker (this is the whole basis of the diff)
Read .agent/seed_prompt.md and pull its header comment:
<!-- seed-tier: <Master|Lite|Compact>; language: <…>; version: v2.5.x; date: …; counterpart: … -->
- No file → not an upgrade: route to
/eg-bootstrap(new) or/eg-migration(existing rules). Stop. - File but no version marker → the seed was hand-edited or truncated. Say so, and offer a re-install of the same tier as the recovery path — do not guess a version.
Record (tier, language, from_version).
1. Compute the delta from the upstream changelog
The changelog is the SSoT for what changed between releases (the seed files carry only a marker, deliberately):
https://raw.githubusercontent.com/SoliEstre/EstreGenesis/main/CHANGELOG.md
Fetch it, find the current release, and collect every entry newer than from_version. Two axes move at different rates — keep them separate:
- Seed marker (
v2.5.xon the seed files) — bumps only when the seed content changes. Most releases do not touch it. - Release version (the repo's
vX.Y.Z) — bumps every meaningful cut, including module-only cuts that do not affect the seed at all.
If the seed marker did not move, say that plainly: the project's charter is already current and only the module/plugin layer needs attention. That is the common case and it is not a failure.
2. Present the delta as a numbered menu (additive only)
Run the seed's Migration B: present the changes as a numbered menu and let the human pick. Menu prose follows Hyperbrief's setup-flow choice default (§5.6.9 — plain floor band, per-item cost/benefit, "explain more simply" fallback). The discipline that makes this safe:
- Additive only. Nothing the project already wrote is overwritten by the upgrade. Deltas add sections, add registry rows, add rules.
- Per-item choice. The user takes items individually — a delta menu is not an all-or-nothing patch.
- Local edits win. Where the project diverged from the seed on purpose, the divergence stands; note it and move on.
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 · 63 lines · 95 tokens per session scan A 249606879798
eg-upgrade is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 95 tokens to every session and 953 once invoked, about $0.0005 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…
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.
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.
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?".