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/config-showgit 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/config-show)<a href="https://agentmods.dev/commands/proticom/gnosys/config-show"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/config-show.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 | $0.00471 |
| Opus 5 | $0.00000 | $0.00235 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
config-show 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 3d 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 config show
Show the current LLM configuration for the first active Gnosys store.
Usage
gnosys config show
gnosys config show --json
Behavior
- Reads config from the first active store returned by the resolver.
- Exits with
No stores found. Run gnosys init first.when no stores are available. - Default output prints the System of Cognition (SOC) summary: default provider, per-provider models and key sources, and task routing for structuring/synthesis.
- With
--json, prints the effective config object as formatted JSON (for scripts and automation). - Read-only: does not modify
gnosys.json.
Output example
System of Cognition (SOC) — LLM Configuration:
Default provider: openai
Providers:
Anthropic: model=claude-sonnet-4-20250514, apiKey=env
OpenAI: model=gpt-4.1, apiKey=config, url=https://api.openai.com/v1
...
Task Routing:
Structuring: openai/gpt-4.1-mini (override)
Synthesis: openai/gpt-4.1 (default)
With --json, output is the parsed config object (pretty-printed).
Platform notes
macOS
- Config is read from
<first-store-path>/gnosys.json(typically project./.gnosysor personal~/.gnosys). - API key columns show
config,env, or—depending on whether keys are in the file or environment.
Linux
- Same store resolution as macOS. Ensure
gnosys inithas been run or a.gnosysdirectory exists before callingconfig show.
Windows
- Store paths may appear with backslashes in resolver output; config loading works the same.
- Environment variables for provider keys (
OPENAI_API_KEY, etc.) are detected the same way as on Unix.
Validation
cd gnosys-public
npm run cli -- config show --help
npm run cli -- config show
npm run cli -- config show --json
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.
- 3d ago First seen · 62 lines · 0 tokens per session scan A 18ed8a1479f7
config-show 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 471 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
test-e2e
Write end-to-end tests for critical user journeys.
test-integration
Write integration tests for component boundaries.
export
Design public API exports.
newpkg
Generate new package with Nx.
cb-search
코드브레인 BM25 검색 — stale 자동 refresh.
decide
Capture a strategic decision so it never gets lost or reopened accidentally.