A workflow for opening an ALIVE project, called a “walnut,” and loading its current context. It reads key project files, resolves the people involved, reports the state, and asks what to work on.

Use it to choose a project from a grouped list, review its goal and phase, see active work, and start the next task.

It helps you resume work with the relevant background instead of searching through every project file. It also surfaces one useful observation, such as a stale blocker or urgent task.

alive-load — Skill for Claude Code and Codex by alivecontext: A workflow for opening an ALIVE project, called a…

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-load

Any agent

npx skills add alivecontext/alive --skill alive-load

Clone the repo

git clone --depth 1 https://github.com/alivecontext/alive

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alivecontext/alive/alive-load.svg)](https://agentmods.dev/skills/alivecontext/alive/alive-load)

Your own site

<a href="https://agentmods.dev/skills/alivecontext/alive/alive-load"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-load.svg" alt="Measured on agentmods" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 567 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.

Model	Per session	Once invoked
Fable 5	$0.00026	$0.00567
Opus 5	$0.00013	$0.00283
Sonnet 5	$0.00005	$0.00113
Haiku 4.5	$0.00003	$0.00057

Measured 3d ago against content hash 3bbaa2f273b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alive-load 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 3d 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-load/SKILL.md · 77 lines

What it actually says

Load Walnut

Load a walnut's context. Read the brief pack, resolve people, surface one observation, ask what to work on.

If No Walnut Named

List available walnuts grouped by domain. Use terminal to run:

find "$ALIVE_WORLD_ROOT" -name "key.md" -path "*/_kernel/*" | grep -v "01_Archive" | sort

Show as a numbered list. Let the user pick.

Brief Pack (3 files)

Read these three files for the named walnut. Nothing else at this stage.

_kernel/key.md -- full (identity, people, links, rhythm)
_kernel/now.json -- full (phase, bundles, tasks, sessions, blockers)
_kernel/insights.md -- first 20 lines only (frontmatter, section names)

Show what you read:

> key.md           [walnut name] -- [type], [rhythm], [N] people
> now.json         Phase: [phase]. Urgent: [N] / Active: [N]. Bundles: [N] active.
> insights.md      [N] domain knowledge sections

Spotted

One observation grounded in what you just read. A stale blocker, an urgent task that has been sitting, a bundle with no recent sessions. If nothing genuine, skip it.

Then Ask

[walnut name]
  Goal:    [from key.md]
  Phase:   [from now.json]
  Bundle:  [active bundle name] ([status])

  What are you working on?
  1. Continue active bundle
  2. Start new
  3. Go deeper (log, linked walnuts)
  4. Just chat

If no active bundle exists, drop option 1 and renumber so the menu is 1. Start new 2. Go deeper 3. Just chat.

During Work

Stash decisions, tasks, notes in conversation
Watch for people updates, bundle fits, capturable content
When another walnut is mentioned, ask before loading it

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.

3d ago First seen · 77 lines · 26 tokens per session scan A 3bbaa2f273b8

Subscribe to this mod's changes

alive-load is a skill published in the GitHub repository alivecontext/alive (127 stars, last pushed 8d ago), licensed MIT. It adds 26 tokens to every session and 567 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.

Memory and context ai-tools claude-code claude-code-plugin cli context-management markdown

crit-cli

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…

tomasz-tomczyk/crit · 110 tokens

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.

tomasz-tomczyk/crit · 55 tokens

alive-load