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/addgit clone --depth 1 https://github.com/proticom/gnosysWhat 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 | $0.00611 |
| Opus 5 | $0.00000 | $0.00305 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
add 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gnosys add
Add a new memory from raw text or an existing file path.
Usage
gnosys add "Decision: use SQLite as source of truth"
gnosys add ./whitepaper.pdf --author human --authority imported --store project
gnosys add ./meeting-notes.txt --store personal
gnosys add "Quick note" -a human --authority declared
Options
| Option | Description |
|---|---|
-a, --author <author> |
Author: human, ai, or human+ai (default human) |
--authority <authority> |
Authority: declared, observed, imported, or inferred (default declared) |
-s, --store <store> |
Target store: project, personal, or global |
Behavior
Raw text input
When <input> is not an existing file path:
- Requires a writable store and an available LLM provider.
- Loads the tag registry and structures the text via
GnosysIngestion. - Inserts the memory into the central DB with generated ID, category, tags, and confidence.
- Prints memory metadata and any proposed new tags not yet in the registry.
File path input
When <input> exists on disk:
- Routes through multimodal ingestion (
ingestFile, modellm). - Prints file type, memory count, duration, memory IDs/titles, and chunk errors if any.
- Does not require the raw-text LLM structuring path (uses file ingestion pipeline).
Common
- Exits with
No writable store found...when no writable store matches--store(or default resolution). - Exits with LLM unavailable error for raw text when no provider is configured.
Output example (raw text)
Structuring memory via LLM...
Memory added to [project]: Decision: use SQLite as source of truth
ID: deci-001
Category: decisions
Confidence: 0.85
Platform notes
macOS
- File paths may be relative or absolute;
existsSyncdetermines file vs text routing. - PDF and other supported formats use the multimodal pipeline.
Linux
- Quote inputs with spaces:
gnosys add "my note here". - Ensure
GNOSYS_PERSONALor project.gnosysexists for writable store.
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 · 85 lines · 0 tokens per session scan A 5fcd7767f66c
add is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 611 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 2026-08-31.
Other commands, from other repositories
init-project
Configure this project for Obsidian PKM — connects the repo to a vault project folder and writes CLAUDE.md integration directives.
setup
Configure Vault PKM plugin — set vault path, API keys, and verify setup.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
competitive-landscape
Map the competitive landscape for a market or company.