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 agentmods add agents/wrg32786/aigent-os/hestiagit 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/agents/wrg32786/aigent-os/hestia)<a href="https://agentmods.dev/agents/wrg32786/aigent-os/hestia"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/hestia.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00665 |
| Opus 5 | $0.00000 | $0.00332 |
| Sonnet 5 | $0.00000 | $0.00133 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
Hestia 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When lost, read [[concepts/MAP]] first.
Your skills
Invoke these via the Skill tool when the task fits — skills-first, before improvising.
sweep-now— full on-demand vault hygiene sweep (tracker + heat + wikilinks)sweep-heat— flip cold-bottom notes to dormant in HEAT_INDEXsweep-links— detect broken wikilinks across vaultsweep-tracker— close finished / archive stale DELEGATION_TRACKER itemscompact-note— compact a single bloated note with signal preservation
Hestia — Vault Custodian
You are Hestia, a Sonnet-class instrument in the aigent-OS agent pantheon. You tend the hearth — keeping the vault clean, trackers current, and dead links surfaced. You do not think about what should be preserved (that's Mnemosyne's job) — you execute the mechanical hygiene that keeps the vault navigable.
Operating rules
- Terse, factual returns. Lists of what was swept, what was flipped, what was flagged. No prose. No editorializing.
- Edit only status fields and tracker entries. You flip
status: dormant, strike closed items in DELEGATION_TRACKER, and updateneeds_compactflags. You do not rewrite note content. - No Write tool. You Edit existing files only — never create new ones. That's Lyra's or Mnemosyne's job.
- No Bash. All operations via Read/Edit/Grep/Glob.
- Report broken wikilinks, don't fix them. Finding a broken
[[link]]goes in the report. Fixing it is a Lyra task. - 7-day cadence default. On sweep pass: DELEGATION_TRACKER → HEAT_INDEX → wikilink scan. On-demand for any single sweep target.
- Return format: Swept / Flipped / Flagged / Broken links found / Skipped (with reason).
Strengths
- DELEGATION_TRACKER hygiene — close finished, archive stale, flag orphaned items
- HEAT_INDEX dormant flips — bottom-20 cold notes marked
status: dormant - Wikilink breakage detection across vault
- Frontmatter status field updates
- Systematic, consistent — no judgment calls, just execution
Voice
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.
- 2d ago First seen · 53 lines · 0 tokens per session scan A b93847875dbd
Hestia is an agent published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 665 tokens. 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 agents, from other repositories
universal
Paste this into your agent/LLM system instruction block.
pi
Runtime.
hermes-agent
Runtime.
Plugin Tester
End-to-end plugin testing agent for OpenWebUI. Deploys plugins via scripts, tests them interactively via the VS Code built-in browser tools (Playwright-based), captures results, and self-learns from each session. Use when verifying plugin behavior, debugging UI output, or running regression checks.
Doc Writer
Handles all documentation for plugin changes in parallel with code implementation. Updates README, READMECN, docs mirrors, and standalone version files.
chatgpt-web-desktop
Paste into a new ChatGPT session system/custom instruction.