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/doctorgit 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/doctor)<a href="https://agentmods.dev/commands/proticom/gnosys/doctor"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/doctor.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
doctor 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 4d 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.
What it actually says
gnosys doctor
Check Gnosys system health: stores, central DB, archive, recall/SOC config, LLM connectivity, embeddings, and maintenance health.
Usage
gnosys doctor
gnosys doctor --fix
Behavior
- Prints a read-only health report by default (no files modified).
- Central DB: migration status, schema version, memory counts.
- Stores: lists active stores and memory counts per store.
- Archive: two-tier memory stats when available.
- Recall: aggressive vs filtered mode, max memories, min relevance.
- SOC: default provider and task routing (structuring/synthesis).
- LLM connectivity: tests each configured provider.
- Embeddings: index size or empty/not-initialized state.
- Maintenance health: stale-memory and reinforcement stats from central DB.
- Legacy local
gnosys.db: warns if a pre-v2.0 per-store DB file exists. --fix: when a legacy localgnosys.dbis found, verifies it is safe to remove (empty or all IDs present in central DB), then prompts interactively before deletion.
Output example
Gnosys Doctor
=============
Central DB (~/.gnosys/gnosys.db):
Status: ✓ migrated (schema v...)
Active: 42 | Archived: 3 | Total: 45
Stores:
project: 12 memories (/path/to/.gnosys)
...
Platform notes
macOS
- Central DB path shown as
~/.gnosys/gnosys.db. - Legacy per-store DB cleanup with
--fixuses an interactive[y/N]prompt in the terminal.
Linux
- Same checks as macOS. Requires
better-sqlite3for central DB and archive sections.
Windows
- Paths may display with backslashes; behavior is equivalent.
- Interactive
--fixprompt works in PowerShell and cmd.
Validation
cd gnosys-public
npm run cli -- doctor --help
npm run cli -- doctor
Related commands
gnosys check— test LLM connectivity per task type.gnosys upgrade— migrate central DB when doctor reports not migrated.
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.
- 4d ago First seen · 69 lines · 0 tokens per session scan A ed915bc08d2e
doctor is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed yesterday), 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 2026-08-31.
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.
checkpoint
Create or update .memory/ with current conversation state.
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.