alive-create

A setup routine for creating a new “walnut”, a named folder for a venture, experiment, person, life area, or project. It records the walnut’s goal, schedule, and starting notes.

In plain words
What is it for?
Use it to create and initialize a new area of work or life with its name, purpose, review rhythm, and first log entry.
Why use it?
It removes the need to design the folder structure and tracking files by hand when starting something new.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/alivecontext/alive/alive-create
Any agent
npx skills add alivecontext/alive --skill alive-create
Clone the repo
git clone --depth 1 https://github.com/alivecontext/alive

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.00588
Opus 5 $0.00010 $0.00294
Sonnet 5 $0.00004 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 2d ago against content hash 94db7cde7864, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alive-create 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 2d 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.

hermes/hermes-skills/alive-create/SKILL.md · 112 lines

What it actually says

Create Walnut

Something new is emerging. It needs its own walnut.

Ask

What kind of walnut?
  1. Venture (04_Ventures/) -- revenue intent
  2. Experiment (05_Experiments/) -- testing grounds
  3. Person (02_Life/people/) -- someone entering the orbit
  4. Life area (02_Life/) -- personal goal or domain
  5. Project (nested under existing walnut)

Then ask:

  • Name: kebab-case (e.g., nova-station)
  • Goal: one sentence
  • Rhythm: daily / weekly / biweekly / monthly

Scaffold

Create via terminal:

WALNUT_PATH="$ALIVE_WORLD_ROOT/[domain]/[name]"
mkdir -p "$WALNUT_PATH/_kernel"

Write three kernel files:

key.md

---
type: [venture/experiment/person/life/project]
goal: [one sentence]
created: [today]
rhythm: [rhythm]
people: []
tags: []
links: []
---

[Brief description of what this walnut is about.]

log.md

---
walnut: [name]
created: [today]
last-entry: [today]
entry-count: 1
summary: Walnut created.
---

## [today] -- squirrel:[session_id]

**Type:** creation

Walnut created. [Goal]. [Any initial context from conversation.]

signed: squirrel:[session_id]

insights.md

---
walnut: [name]
updated: [today]
squirrel: [session_id]
sections: []
---

tasks.json + completed.json

echo '{"tasks": []}' > "$WALNUT_PATH/_kernel/tasks.json"
echo '{"completed": []}' > "$WALNUT_PATH/_kernel/completed.json"

Run projection

python3 "$ALIVE_WORLD_ROOT/.alive/scripts/project.py" --walnut "[relative_path]"

After Creation

  • If this walnut is a sub-walnut, add parent: [[parent]] to key.md
  • Add [[name]] to parent's key.md links
  • Offer to create the first bundle
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. 2d ago First seen · 112 lines · 19 tokens per session scan A 94db7cde7864

Subscribe to this mod's changes

alive-create is a skill published in the GitHub repository alivecontext/alive (127 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 588 once invoked, about $0.0001 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 2026-08-30.