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 commands/proticom/gnosys/web-updategit clone --depth 1 https://github.com/proticom/gnosysWrote 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/commands/proticom/gnosys/web-update)<a href="https://agentmods.dev/commands/proticom/gnosys/web-update"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/web-update.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 | $0.00488 |
| Opus 5 | $0.00000 | $0.00244 |
| Sonnet 5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
web-update 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
gnosys web update
Re-ingest a URL or refresh a local knowledge file, then rebuild the search index.
Usage
gnosys web update https://example.com/page
gnosys web update blog/example-page.md
gnosys web update https://example.com/page --category blog --no-llm --json
Arguments
| Argument | Description |
|---|---|
urlOrPath |
HTTP(S) URL to re-ingest, or path relative to the knowledge directory for local refresh |
Prerequisites
Run gnosys web init first so gnosys.json contains a web configuration.
Options
| Option | Description |
|---|---|
--no-llm |
Force structured mode (skip LLM enrichment) |
--category <name> |
Override category inference for URL ingest |
--json |
Output result as JSON |
URL branch
- Re-ingests via
ingestUrlwithsource: "urls", config output dir, optional category override, LLM from config unless--no-llm. - Rebuilds index to
<knowledgeRoot>/gnosys-index.json.
Local path branch
- Resolves path against
knowledgeRoot. - Rejects absolute paths and
../traversal outside the knowledge directory. - Verifies file exists, then rebuilds index.
Human output
URL:
Updated: https://example.com/page
Added: 1, Updated: 0
Index rebuilt: 42 documents
Local:
Refreshed: blog/example-page.md
Index rebuilt: 42 documents
JSON output
URL success includes ingest result fields plus documentCount. Local success:
{
"ok": true,
"refreshed": "blog/example-page.md",
"documentCount": 42
}
Validation
cd gnosys-public
npm run cli -- web update --help
npx vitest run src/test/web-update-command-handler.test.ts
Related commands
gnosys web add— ingest a single URL without full update flow.gnosys web build-index— rebuild index only.
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 · 83 lines · 0 tokens per session scan A 283f16e63775
web-update is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 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 commands, from other repositories
embed
Generate text embeddings for semantic search and similarity.
agent-brain-index
Index documents for semantic search.
agent-brain-vector
Search using semantic vector similarity for concepts.
agent-brain-providers
List and configure embedding and summarization providers.
agent-brain-semantic
Search using semantic vector similarity for conceptual queries.
ingest
Manually add knowledge to the Weaviate store.