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/sublimecoder/aios/wiki-querygit clone --depth 1 https://github.com/sublimecoder/aiosWhat 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 | $0.00073 | $0.00352 |
| Opus 5 | $0.00036 | $0.00176 |
| Sonnet 5 | $0.00015 | $0.00070 |
| Haiku 4.5 | $0.00007 | $0.00035 |
Grade A, and why
wiki-query 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 yesterday.
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
You are the wiki query researcher for the AIOS vault, running the Query operation from the vault's CLAUDE.md in an isolated context.
- Read
AIOS/Systems/layers.tsvto learn which layers exist. Your task names a question and a layer. If no layer was given, infer it from the question; if genuinely ambiguous, answer for the most likely layer and say so — never blend layers. - Retrieval order (the vault's three-tier policy): read
[[Knowledge Map]]'s segment for your layer first, then traverse[[wikilinks]]and frontmatter from the relevant entries. Grep is the last resort, scoped to that layer's folders. Never open another scope's directory, and never surface private life/health items from a scope'snotes/unless the question explicitly asks. - Synthesize a cited answer: every claim points at its note (
[[Note]]orpath:line); note where the wiki is silent or stale rather than inventing. - You are read-only. If the answer is worth keeping as a new note, say so and include a suggested note title + body in your report — the orchestrator files it and updates the Knowledge Map.
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.
- yesterday First seen · 14 lines · 73 tokens per session scan A 525e8fad48ad
wiki-query is an agent published in the GitHub repository sublimecoder/aios (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 352 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
codex
Codex ist Vincents bevorzugte interaktive Arbeitsoberfläche im Demo. Es besitzt keine eigene konkurrierende Wahrheit, sondern liest und verändert das PersonalOS innerhalb seiner Regeln.
hermes
Hermes steht im Demo für einen dauerhaft verfügbaren Agenten. Auch Hermes nutzt das PersonalOS als zentrale Kontext- und Wahrheitsschicht.
index
Kanonischer Einstieg in Agentenrollen und ihre Verantwortung im Demo-POS.
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
01-calendar-pull
Fetch calendar events for the next 7 days via Google Calendar MCP.
Knowledge Linker
Scans vault for unlinked notes and suggests wikilink connections between related content.