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/helper-generategit 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/helper-generate)<a href="https://agentmods.dev/commands/proticom/gnosys/helper-generate"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/helper-generate.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 | $0.00353 |
| Opus 5 | $0.00000 | $0.00177 |
| Sonnet 5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
helper-generate 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 helper generate
Generate a gnosys-helper.ts file for direct sandbox access from agent scripts.
Usage
gnosys helper generate
gnosys helper generate --directory ./agent
gnosys helper generate --json
Options
| Option | Description |
|---|---|
-d, --directory <dir> |
Target directory (default: current working directory) |
--json |
Output result as JSON |
Behavior
- Resolves target directory from
--directoryorprocess.cwd(). - Calls
generateHelper(targetDir)to write the helper file. - Prints usage hints or JSON result.
Human output
Generated: /path/to/gnosys-helper.ts
Usage in your agent/script:
import { gnosys } from "./gnosys-helper";
await gnosys.add("We use conventional commits");
const ctx = await gnosys.recall("auth decisions");
JSON output
Success:
{
"ok": true,
"path": "/path/to/gnosys-helper.ts"
}
Failure:
{
"ok": false,
"error": "error message"
}
On failure without --json, prints Failed to generate helper: ... to stderr and exits with code 1.
Validation
cd gnosys-public
npm run cli -- helper generate --help
npx vitest run src/test/helper-generate-command-handler.test.ts
Related commands
gnosys sandbox start— start the sandbox the helper connects to.
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 · 70 lines · 0 tokens per session scan A ad3012b059d8
helper-generate 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 353 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.
start
"What accumulated? What's blocking? Where do I begin?".
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.
gains
Show what Kage saved you — tokens, cost, stale memories blocked, stale knowledge caught.