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 alivecontext/alive --skill alive-creategit clone --depth 1 https://github.com/alivecontext/aliveWrote 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/alivecontext/alive/alive-create)<a href="https://agentmods.dev/skills/alivecontext/alive/alive-create"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-create/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/alivecontext/alive/alive-create"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-create.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 | $0.00019 | $0.00588 |
| Opus 5.5 | $0.00008 | $0.00235 |
| Sonnet 5.5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
alive-create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Create Walnut
Something new is emerging. It needs its own walnut.
Ask
What kind of walnut?
1. Venture (04_Ventures/) -- revenue intent
2. Experiment (05_Experiments/) -- testing grounds
3. Person (02_Life/people/) -- someone entering the orbit
4. Life area (02_Life/) -- personal goal or domain
5. Project (nested under existing walnut)
Then ask:
- Name: kebab-case (e.g.,
nova-station) - Goal: one sentence
- Rhythm: daily / weekly / biweekly / monthly
Scaffold
Create via terminal:
WALNUT_PATH="$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
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.
- 1mo ago First seen · 112 lines · 19 tokens per session scan A 94db7cde7864
alive-create is a skill published in the GitHub repository alivecontext/alive (130 stars, last pushed 15d ago), licensed MIT. It adds 19 tokens to every session and 588 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
kn-handoff
Use when a feature crosses repository boundaries and one side must hand work to the other - generates a self-contained frontend-to-backend brief or backend-to-frontend API contract.
product
Apply product thinking to platform work — DevEx audits, friction analysis, RFC/ADR drafting, incident communication, post-mortems, capacity planning, cost optimisation, and platform health review.
cco-orchestrate
Run a task as a cost-aware orchestrator — cheap Haiku subagents do the reading, searching and test runs; the main model plans, edits and decides.
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.