alive-search

alive-search is a skill for Claude Code, Codex from alivecontext/alive. It costs 20 tokens per session (511 once invoked), scanned A, original, MIT.

A search tool for an Alive knowledge system called “walnuts,” including its decisions, people, files, references, insights, and history logs. It searches the system’s stored notes and manifests.

In plain words
What is it for?
Use it to find past decisions, people records, filenames, project references, insights, identities, and related log entries.
Why use it?
It helps locate information that may be spread across different notes, folders, or records instead of being in one document.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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-search
Any agent
npx skills add alivecontext/alive --skill alive-search
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.

agentmods badge for alive-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivecontext/alive/alive-search.svg)](https://agentmods.dev/skills/alivecontext/alive/alive-search)
Your own site
<a href="https://agentmods.dev/skills/alivecontext/alive/alive-search"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 511 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 5.1 $0.00020 $0.00511
Opus 5 $0.00010 $0.00255
Sonnet 5 $0.00004 $0.00102
Haiku 4.5 $0.00002 $0.00051

Measured 6d ago against content hash da605d987b75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

alive-search 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 6d 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-search/SKILL.md · 75 lines

What it actually says

Search World

Find something that exists somewhere in the world.

Search Priority

  1. Decisions -- search _kernel/log.md across all walnuts
  2. People -- search 02_Life/people/ walnut names and key.md
  3. Files -- search filenames and bundle manifests
  4. Insights -- search _kernel/insights.md across all walnuts
  5. Identities -- search _kernel/key.md across all walnuts

Method

Use terminal to search:

# Search logs
grep -rl "[query]" "$ALIVE_WORLD_ROOT"/*/_kernel/log.md "$ALIVE_WORLD_ROOT"/*/*/_kernel/log.md 2>/dev/null

# Search insights
grep -rl "[query]" "$ALIVE_WORLD_ROOT"/*/_kernel/insights.md "$ALIVE_WORLD_ROOT"/*/*/_kernel/insights.md 2>/dev/null

# Search people
grep -rl "[query]" "$ALIVE_WORLD_ROOT"/02_Life/people/*/_kernel/key.md 2>/dev/null

# Search bundle manifests
grep -rl "[query]" "$ALIVE_WORLD_ROOT"/*/context.manifest.yaml "$ALIVE_WORLD_ROOT"/*/*/context.manifest.yaml 2>/dev/null

Display Results

Found [N] matches for "[query]":

Logs:
  [walnut] -- [matching snippet with date]
  [walnut] -- [matching snippet with date]

People:
  [[person-name]] -- [role, last updated]

Insights:
  [walnut] -- [matching section]

Load any of these?
  1. [walnut name]
  2. [[person name]]
  3. Search again with different terms

Skip Archive

Exclude 01_Archive from results by default. Mention if matches exist there: "Also found in archive: [walnut]".

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. 6d ago First seen · 75 lines · 20 tokens per session scan A da605d987b75

Subscribe to this mod's changes

alive-search is a skill published in the GitHub repository alivecontext/alive (127 stars, last pushed 10d ago), licensed MIT. It adds 20 tokens to every session and 511 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.

Related

Other skills, from other repositories