alive-prune

alive-prune is a skill for Claude Code, Codex from alivecontext/alive. It costs 16 tokens per session (415 once invoked), scanned A, original, MIT.

A weekly maintenance review for a personal knowledge system. It checks activity logs, saved insights, and unfinished bundles for items that may need summarising, archiving, removing, or advancing.

In plain words
What is it for?
Use it to suggest chapter summaries for long logs, flag insights not recently referenced, and review draft bundles older than 30 days.
Why use it?
It brings attention to accumulated or stale information without deleting anything automatically. This helps keep long-running notes useful and manageable.

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-prune
Any agent
npx skills add alivecontext/alive --skill alive-prune
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-prune

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivecontext/alive/alive-prune.svg)](https://agentmods.dev/skills/alivecontext/alive/alive-prune)
Your own site
<a href="https://agentmods.dev/skills/alivecontext/alive/alive-prune"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-prune.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 415 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 $0.00016 $0.00415
Opus 5 $0.00008 $0.00208
Sonnet 5 $0.00003 $0.00083
Haiku 4.5 $0.00002 $0.00042

Measured 5d ago against content hash f144231e8d1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alive-prune 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 5d 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/cron-templates/alive-prune/SKILL.md · 73 lines

What it actually says

Weekly Prune

Suggest maintenance actions for log and insight hygiene.

Process

Log Chapter Synthesis

For each walnut, check _kernel/log.md:

  • Count entries (## headings after frontmatter)
  • If 50+ entries, suggest chapter synthesis
[walnut] log has [N] entries.
  Suggest synthesizing older entries into _kernel/history/chapter-[nn].md?
  1. Yes, synthesize
  2. Not yet

Stale Insights

For each walnut, check _kernel/insights.md:

  • Read each section
  • Flag sections not referenced in recent log entries (last 30 days)
[walnut] insights:
  "[section name]" -- not referenced in 45 days
  1. Keep (still relevant)
  2. Archive (move to bottom)
  3. Remove

Stale Bundles

Find bundles in draft status older than 30 days:

[walnut]/[bundle] -- draft for 42 days
  1. Advance (prototype)
  2. Archive (done)
  3. Kill (delete)
  4. Leave

Output

If nothing needs attention: [SILENT]

If issues found, present one category at a time. Keep actionable.

Rules

  • This is weekly, not urgent. Present calmly.
  • Never auto-prune. Always suggest and wait.
  • Chapter synthesis preserves full entries -- it's summarization, not deletion.
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. 5d ago First seen · 73 lines · 16 tokens per session scan A f144231e8d1f

Subscribe to this mod's changes

alive-prune is a skill published in the GitHub repository alivecontext/alive (127 stars, last pushed 9d ago), licensed MIT. It adds 16 tokens to every session and 415 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.