sweep-heat

sweep-heat is a skill for Claude Code from wrg32786/aigent-os. It costs 47 tokens per session (513 once invoked), scanned A, original, MIT.

A memory-maintenance task that reads a heat index and marks the least-used notes as dormant. It updates note metadata without changing the note content.

In plain words
What is it for?
Use it to scan the 20 least-accessed notes in a knowledge vault, update eligible frontmatter, and report how many notes changed.
Why use it?
It reduces clutter by identifying cold notes and separating them from active knowledge. It also avoids changing notes that are protected or already dormant.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Good fit Use it to scan the 20 least-accessed notes in a knowledge vault, update eligible frontmatter, and report how many notes changed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wrg32786/aigent-os/sweep-heat
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.

Any agent
npx skills add wrg32786/aigent-os --skill sweep-heat
Clone the repo
git clone --depth 1 https://github.com/wrg32786/aigent-os

Made for: Claude Code.

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 sweep-heat

README.md
[![agentmods](https://agentmods.dev/badge/skills/wrg32786/aigent-os/sweep-heat/github.svg)](https://agentmods.dev/skills/wrg32786/aigent-os/sweep-heat)
Your own site
<a href="https://agentmods.dev/skills/wrg32786/aigent-os/sweep-heat"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/sweep-heat/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.

agentmods 80×15 button for sweep-heat

Your own site · 80×15
<a href="https://agentmods.dev/skills/wrg32786/aigent-os/sweep-heat"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/sweep-heat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00047 $0.00513
Opus 5 $0.00023 $0.00257
Sonnet 5 $0.00009 $0.00103
Haiku 4.5 $0.00005 $0.00051

Measured 9d ago against content hash 220425edef3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sweep-heat 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 9d 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.

skills/sweep-heat/SKILL.md · 66 lines

What it actually says

Sweep Heat

You are Hestia sweeping the HEAT_INDEX and flipping cold notes to dormant. Terse. Factual. No editorializing.

What this skill does

Read memory/HEAT_INDEX.md (or the path specified). Identify the cold bottom-20 notes. Add status: dormant to their frontmatter. Return counts of what was flipped.

Protocol

Step 1: Read HEAT_INDEX

Read memory/HEAT_INDEX.md to identify the bottom-20 cold notes. These are the notes with the lowest access/link frequency scores.

Step 2: Read each cold note's frontmatter

For each of the bottom-20 notes, Read the file to check current frontmatter. Specifically look for the status: field.

Step 3: Flip eligible notes

A note is eligible for dormant flip if:

  • It has a status: field (or no status field — add one)
  • Its current status is NOT active, pinned, protected, or dormant
  • It is a vault note (not a third-party file, tool, or LICENSE)

Use Edit to add or update: status: dormant

Skip: third-party files, tool config files, LICENSE files, files outside the vault.

Step 4: Return report (terse)

## Heat Sweep — YYYY-MM-DD

Bottom-20 scanned: 20
Flipped to dormant: N
Skipped (already dormant): N
Skipped (protected/active/pinned): N
Skipped (non-vault file): N

Constraints

  • Edit only the status: frontmatter field. No content edits.
  • No Write tool. No new files.
  • No Bash, no Agent, no WebFetch.
  • Third-party files are never touched.
  • Report is counts and brief list only. No prose.
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. 9d ago First seen · 66 lines · 47 tokens per session scan A 220425edef3a

Subscribe to this mod's changes

sweep-heat is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 513 once invoked, about $0.0002 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 2026-09-03.