eg-bootstrap

eg-bootstrap is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 128 tokens per session (2,796 once invoked), scanned A, original, Apache-2.0.

A setup procedure for putting a new or nearly empty project onto the EstreGenesis operating standard.

In plain words
What is it for?
Use it to choose and install the right seed, create the project’s AGENTS.md and .agent structure, and run the seed’s initial setup mode.
Why use it?
It installs a project charter and supporting structure so the agent has documented rules for how it should work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions AGENTS.md.

Part of the estregenesis plugin — 13 skills shipped together

Good fit Use it to choose and install the right seed, create the project’s AGENTS.md and .agent structure, and run the seed’s initial setup mode.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soliestre/estregenesis/eg-bootstrap
Install

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.

Any agent
npx skills add SoliEstre/EstreGenesis --skill eg-bootstrap
Clone the repo
git clone --depth 1 https://github.com/SoliEstre/EstreGenesis

Made for: Claude Code.

Or install estregenesis, the plugin that ships this one along with the rest of its 13 skills.

Wrote 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.

agentmods badge for eg-bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/skills/soliestre/estregenesis/eg-bootstrap.svg)](https://agentmods.dev/skills/soliestre/estregenesis/eg-bootstrap)
Your own site
<a href="https://agentmods.dev/skills/soliestre/estregenesis/eg-bootstrap"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/eg-bootstrap.svg" alt="Measured on agentmods" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00128 $0.02796
Opus 5 $0.00064 $0.01398
Sonnet 5 $0.00026 $0.00559
Haiku 4.5 $0.00013 $0.00280

Measured 8d ago against content hash b019c5ddf2e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

eg-bootstrap scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Fetch the chosen file (WebFetch, or `curl -fsSL <base><file>`) and write it verbatim to **`.agent/seed_prompt.md`** in the target project. Keep the header comment intact — its `version:` marker is what `/eg-upgrade` diff
plugins/estregenesis/skills/eg-bootstrap/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/eg-bootstrap (/egboot) — start a new project on the EG standard

Bootstrap mode B of the seed. The point of this skill is that you no longer hunt for a GitHub URL and paste a seed by hand — the tier table below is the pointer, and the seed itself remains the single normative source (this skill never restates the seed's rules).

0.0 If you are an autonomous agent and someone just handed you EG

Read this first, because the natural mistake is to treat EG as a task. It is not something to build; it is the layer you operate on. An autonomous agent (a resident gateway, a messaging-attached assistant, a long-lived worker) that receives the seed should install it as its own operating charter and then stop — production work waits for an actual request. Building something to demonstrate EG is the failure mode: you would be producing an artifact nobody asked for while the charter that governs how you record work is still not in place.

Reception, in order:

  1. Install the charter — steps 1-3 below. This is what makes AGENTS.md the single source of truth for how you work here.
  2. Mount the defaults — step 4a. Skills and conduct only; nothing that runs a process.
  3. Say what is available but not on — step 4b, one line. Do not enable any of it yet.
  4. Then wait. The next move belongs to the user.

If the seed is handed to you inside a shared space with other participants (a group chat, a bridged channel), the conduct defaults in step 4a are already in force before you finish reading — in particular, do not answer messages you were not addressed in. See §13.30.9 / /roundtable D10-D12.

0.1 Bootstrap comes before the first deliverable — including non-code projects

When a project has no charter yet and a work request arrives, bootstrap first, then do the work. The reason is ordering, not ceremony: the charter decides where decisions are recorded, how versions are cut, and what the agent may do without asking. Doing the work first means the first decisions land nowhere and get reconstructed later from memory.

Read the full file on GitHub · 117 lines

Changes

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.

  1. 8d ago First seen · 117 lines · 128 tokens per session scan A b019c5ddf2e6

Subscribe to this mod's changes

eg-bootstrap is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,796 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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…

mostlyharmless-ai/watercooler · 203 tokens

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…

mostlyharmless-ai/watercooler · 79 tokens

search-threads

Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.

mostlyharmless-ai/watercooler · 35 tokens

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.

Fatboy-coder/ppgp · 53 tokens

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.

mostlyharmless-ai/watercooler · 49 tokens

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?".

mostlyharmless-ai/watercooler · 41 tokens