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 wrg32786/aigent-os --skill sweep-heatgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/sweep-heat)<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.
<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>- 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 | $0.00047 | $0.00513 |
| Opus 5 | $0.00023 | $0.00257 |
| Sonnet 5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00051 |
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.
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, ordormant - 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.
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.
- 9d ago First seen · 66 lines · 47 tokens per session scan A 220425edef3a
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.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
memory-flush
Promote important recent log entries into MEMORY.md and prune stale ones.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
continuum-memory
Configure and use Continuum's two-tier memory system — mem0+Qdrant/Milvus for long-term facts, Redis for short-term sessions, with multi-tenant scopes (USER / AGENT / SHARED / RUN / CONVERSATION). Invoke when the user asks about "remember", "user preferences", "long-term memory", "vector search over memories"…
carryover
Use when recalling, saving or curating carryover memory, wikis, playbooks or the Obsidian vault.