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 agents/vironnimo/vbot/open-e2e-workergit clone --depth 1 https://github.com/Vironnimo/vbotWhat 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 | $0.00007 | $0.00033 |
| Opus 5 | $0.00003 | $0.00016 |
| Sonnet 5 | $0.00001 | $0.00007 |
| Haiku 4.5 | $0.00001 | $0.00003 |
Grade A, and why
open-e2e-worker 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 yesterday.
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
E2E_OPEN_CODE_AGENT_PROMPT_4172
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.
- yesterday First seen · 7 lines · 7 tokens per session scan A b0d8bd9cd891
open-e2e-worker is an agent published in the GitHub repository Vironnimo/vbot (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 7 tokens to every session and 33 once invoked, about $0.0000 per session on Opus 5. 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 agents, from other repositories
openclaw
Install HM-Arch as OpenClaw's native memory provider. OpenClaw integration uses the @hm-arch/openclaw-plugin TypeScript memory plugin backed by a persistent Python sidecar that exposes HM-Arch recall, capture, forget, and consolidation without per-query process startup.
benchmark-compatibility-matrix
Production benchmark runners invoke each host agent through its real CLI boundary. Deterministic mock runners (mock-synthetic) are reserved for offline harness tests only.
hermes
Install HM-Arch and configure Hermes to use the native HM-Arch Memory Provider. Hermes integration uses native plugin registration. hm-arch install hermes creates the HM-Arch plugin bridge, updates $HERMESHOME/config.yaml, and initializes the SQLite database.
Python Developer
Python developer agent for testing.
compatibility-matrix
HM-Arch integrates with four coding agents. This matrix summarizes what the packaged hm-arch CLI supports today and where manual configuration is required.
codex
Install HM-Arch, wire Codex lifecycle hooks, smoke-test, and uninstall. All steps are offline and do not require API keys.