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/webgit 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)<a href="https://agentmods.dev/commands/proticom/gnosys/web"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/web.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 | $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 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 today.
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
Parent command for the Gnosys web knowledge base — crawl websites or local content, generate searchable markdown knowledge files, build a search index, and optionally add build-time vectors for hybrid semantic search.
Usage
gnosys web
gnosys web init
gnosys web ingest
gnosys web build
gnosys web status
Bare gnosys web (no subcommand) prints Commander help for the available subcommands. The parent command has no runtime .action(...) — all behavior lives in the leaf subcommands below.
The generated gnosys-index.json works as a zero-dependency lexical index in gnosys/web. For hybrid semantic search, build gnosys-vectors.json with gnosys web build --embeddings <provider> and pass a caller-supplied query vector to the runtime search API. See Web semantic search.
Subcommands
| Subcommand | Purpose |
|---|---|
init |
Interactive setup for the web knowledge base |
ingest |
Crawl the configured source and generate knowledge markdown files |
build-index |
Generate search index JSON from the knowledge directory |
build |
Run ingest + build-index in one shot |
add <url> |
Ingest a single URL into the knowledge base |
remove <filepath> |
Remove a knowledge file and rebuild the index |
update <urlOrPath> |
Re-ingest a URL or refresh a knowledge file |
status |
Show the current state of the web knowledge base |
See the leaf command docs for options, output, and error handling:
gnosys web initgnosys web ingestgnosys web build-indexgnosys web buildgnosys web addgnosys web removegnosys web updategnosys web status
Validation
cd gnosys-public
npm run cli -- web --help
npm run cli -- web init --help
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.
- today First seen · 50 lines · 0 tokens per session scan A 14a55771d419
web is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed today), 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
wrap
Close the session cleanly. Update entity state. Capture decisions. Detect momentum shifts.
promote
Move .memory/ artifacts to permanent knowledge locations.
cleanup
Delete promoted content from the .memory/ directory.
perf-investigate
Drive an iOS performance or memory-leak investigation on using Memory Graph + Time Profiler. Enforce data-before-architecture and stacked PRs.
gains
Show what Kage saved you — tokens, cost, stale memories blocked, stale knowledge caught.
krimto-status
Show the current state of Krimto memory — total facts, scope breakdown, recent writes, and index health.