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 egrichgit 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/egrich)<a href="https://agentmods.dev/skills/soliestre/estregenesis/egrich"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/egrich/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/egrich"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/egrich.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 | $0.00103 | $0.01071 |
| Opus 5 | $0.00051 | $0.00535 |
| Sonnet 5 | $0.00021 | $0.00214 |
| Haiku 4.5 | $0.00010 | $0.00107 |
Grade A, and why
egrich 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 9d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/egrich — full arm
The seed alone is deliberately lean: AGENTS.md SSoT + bridges + .agent/, file-based coordination, no modules. /egrich is the opposite end — everything EG ships, wired and checked.
Say the cost out loud before you start. The full stack adds always-on hooks, background processes (a live board server + bridges), and MCP servers. That is the right trade for a project running several agents in parallel; it is overkill for a solo repo. If the user has not clearly asked for "everything", name the cheap subset (§5) and let them choose — presented per Hyperbrief's setup-flow choice default (§5.6.9: plain floor band, costs/benefits + recommendation, "explain more simply" fallback).
1. Ensure the charter exists
If .agent/seed_prompt.md is absent, run /eg-bootstrap (new project) or /eg-migration (existing rules) first, and continue only after it lands. If it is present but behind, run /eg-upgrade first — arming a stale charter just bakes the staleness in.
2. Install the plugin set
/plugin marketplace add SoliEstre/EstreGenesis
/plugin install estregenesis@estregenesis-plugins
/plugin install constellation@estregenesis-plugins
/plugin install superscalar@estregenesis-plugins
/plugin install hyperbrief@estregenesis-plugins
/plugin install greatpractice@estregenesis-plugins
/plugin install ultrasafe@estregenesis-plugins
/plugin install compendium@estregenesis-plugins
3. What each module gives the project — and what it costs
Register each one in AGENTS.md (the module registry table) as you enable it, so the charter stays the SSoT of what is actually on.
| Module | What it does | What it costs |
|---|---|---|
| Constellation | Live board + agent-to-agent messaging: agents coordinate over a shared board instead of stepping on each other | A board server + a bridge process per agent; the heaviest piece |
| Superscalar | Bounds parallel fan-out: how many agents at once, what may run speculatively, what must wait for a write barrier | Discipline only — no runtime |
| Hyperbrief | Decision delegation: when a call is the human's, the agent produces a structured brief instead of a vague question | A hook + an MCP server |
| Greatpractice | Turns recurring work into durable practice (/routinize), with promotion user-gated so nothing over-codifies |
A memory folder + optional hooks |
| Ultrasafe | Pre-release security fan-out: attacker-perspective agents run before a publish-equivalent command | A pre-publish hook; advisory in v0.2.x (never blocks) |
| Compendium | Controlled vocabulary: one definition per concept, plain + expert registers, pointing at the owning spec instead of copying it | A markdown store + a lint |
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.
- 9d ago First seen · 58 lines · 103 tokens per session scan A 360305ff10fb
egrich is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,071 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?".