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 create-walnutgit 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/create-walnut)<a href="https://agentmods.dev/skills/alivecontext/alive/create-walnut"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/create-walnut/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/create-walnut"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/create-walnut.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 | $0.00063 | $0.03961 |
| Opus 5.5 | $0.00025 | $0.01584 |
| Sonnet 5.5 | $0.00013 | $0.00792 |
| Haiku 4.5 | $0.00006 | $0.00396 |
Grade A, and why
alive:create-walnut 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.
How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create
Scaffold a new walnut — any type, any ALIVE domain. Understand it first, map where its context lives, then scaffold. Optionally bring in existing content (Step 7 — only if the human has files to migrate).
Not a setup wizard (that's world/setup.md — first-time only). Not opening an existing walnut (that's alive:load-context).
Template Locations
The squirrel MUST read these templates before writing — not reconstruct from memory. Templates live relative to the plugin install path.
templates/walnut/key.md → _kernel/key.md
templates/walnut/key-codebase.md → _kernel/key.md (codebase variant, Step 2b)
templates/walnut/log.md → _kernel/log.md
templates/walnut/insights.md → _kernel/insights.md
Placeholders
Used in key.md and key-codebase.md:
| Placeholder | Source |
|---|---|
{{type}} |
Step 1 selection |
{{goal}} |
Extracted from Step 2 free text |
{{name}} |
Kebab-case slug derived from Step 2 |
{{date}} |
Current ISO date (YYYY-MM-DD) |
{{description}} |
The human's free text from Step 2, lightly cleaned |
Additional placeholders in key-codebase.md (Step 2b only):
| Placeholder | Source |
|---|---|
{{repo}} |
Repository URL from Step 2b |
{{local_path}} |
Local clone path from Step 2b |
{{github_account}} |
GitHub account or org from Step 2b |
{{stack}} |
Tech stack summary from Step 2b |
{{branch}} |
Default branch name from Step 2b |
Used in entry.yaml (squirrel — written by session-new hook, not by this skill):
| Placeholder | Source |
|---|---|
{{session_id}} |
Current session ID |
{{engine}} |
Current model (e.g. claude-opus-4-6) |
{{walnut}} |
Same as {{name}} |
{{squirrel_name}} |
From preferences.yaml squirrel_name: or null |
{{timestamp}} |
ISO timestamp at session start |
{{transcript}} |
Path to session transcript JSONL |
{{cwd}} |
Working directory at session start |
{{rules_loaded}} |
Count of rules loaded at session start |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 349 lines · 63 tokens per session scan A 086ac797ec9e
alive:create-walnut is a skill published in the GitHub repository alivecontext/alive (130 stars, last pushed 15d ago), licensed MIT. It adds 63 tokens to every session and 3,961 once invoked, about $0.0003 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.
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.
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.