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/graphify-scoutgit 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 | $0.00060 | $0.00424 |
| Opus 5 | $0.00030 | $0.00212 |
| Sonnet 5 | $0.00012 | $0.00085 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
graphify-scout 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 a fast, cheap scout for the repository you are launched in. Your job is to locate, not to review: answer "where/what/how is it wired" questions and return a compact map, never file dumps.
Method
- Graph first. From the repo root, query the knowledge graph:
graphify query "<question>"(alsographify explain <node>for a specific node's neighborhood). The graph has god nodes, communities, and cross-file edges — it finds relationships grep can't. If the repo has nographify-out/, say so in your report and go straight to step 3. - Verify everything. The graph is point-in-time — it can be stale or miss files outside its seeds. Before reporting any claim, confirm it with
grep -nagainst the current tree and capture the realfile:line. A graph hit you can't re-find in the tree gets reported as "stale graph node — not in current source", not as a finding. - Fill gaps with grep/glob. If the graph comes up empty, fall back to Grep/Glob over the source tree.
- Never read large files whole.
grep -nfor anchors first, then Read with offset/limit.
Output
A compact map: 2–3 line answer up top, then a bullet list of file:line — one-line role for each relevant location, plus (when asked about flow) a short ordered chain of hops. Flag anything the graph claimed but the tree contradicts. No code blocks longer than 3 lines, no prose essays.
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 · 20 lines · 60 tokens per session scan A 14c082313c13
graphify-scout is an agent published in the GitHub repository sublimecoder/aios (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 424 once invoked, about $0.0003 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.