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 skills/spytensor/openmozi/self-opsnpx skills add spytensor/openmozi --skill self-opsgit clone --depth 1 https://github.com/spytensor/openmoziWhat 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 | $0.00056 | $0.00748 |
| Opus 5 | $0.00028 | $0.00374 |
| Sonnet 5 | $0.00011 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
self-ops 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Self-Ops
Knowledge for diagnosing and operating this runtime. Verify claims with tools before reporting — never say "database is empty" without querying it.
Database
- Location:
~/.mozi/data/mozi.db(SQLite, WAL mode). But do not assume~/.moziis the active home — check/api/healthfor the realmozi_home. - Inspect:
shell_exec('sqlite3 ~/.mozi/data/mozi.db ".tables"'). - Key tables:
skill_versions,agent_registry,memory_facts,conversations,tasks,event_log,turn_traces,tool_spans,prompt_snapshots,system_state. - Startup sequence: config load → DB init → migrations → bootstrap → workspace skills → channels. Schema evolution must stay additive for legacy DBs.
Observability
- Every turn has a persistent
trace_idinturn_traces; each tool call writes a span intool_spans. - Prompt snapshots are captured per turn into
prompt_snapshots(context slot breakdown, tool set, token budgets) and auto-pruned. - Dashboard APIs:
/api/dashboard/modelsfor model dimensions;/api/dashboard/slo?period=day|week|month&tenantId=...&model=...for success rate, latency, failure categories, cost, and recent traces/spans. - The failure replay harness can export a fixture by
trace_idand generate a regression test skeleton. - Anchor reliability explanations to concrete trace IDs and span failures, not generic summaries.
Timeout Hierarchy
Timeouts are nested; inner fires before outer:
- Tool SLA: per-tool execution timeout (default 60s,
tel.tools). - LLM call: single inference timeout (
tools.loops.llm_call_timeout_ms, default 300s). For CLI-pipe providers this covers the full agent turn. - Turn timeout: end-to-end loop runtime per turn
(
tools.loops.max_elapsed_ms, default 600s), checked between iterations. - Channel timeout: channel-level guard (e.g.
telegram.interactive_turn_timeout_ms, default 600s).
Process Management
- Restart ONLY via the
restart_selftool. NEVER viashell_execwithpnpm mozi stop/start/restart— that kills your own process and leaves the runtime offline. - Runtime service state:
/api/runtime/servicefor installed/enabled/active status. Do not infer always-on behavior from the presence of a plist/unit path. - Token budgets are model-aware and auto-compact at watermarks; oversized output requests are clamped before dispatch.
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 · 68 lines · 56 tokens per session scan A f5b924c4837c
self-ops is a skill published in the GitHub repository spytensor/openmozi (210 stars, last pushed 26d ago), licensed MIT. It adds 56 tokens to every session and 748 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
lobu-operator
Contribute safely to the Lobu monorepo: worktrees, package rules, red-to-green fixes, validation gates, SDK-first operations, PRs, and rollout checks.
company-agent-infrastructure
Use when designing or building internal/company AI agents that need shared context across company systems, durable organizational memory across sessions or agents, user-scoped permissions, approvals, audit, or governed actions. Also use when deciding whether ordinary MCP tools, RAG, or local agent memory are enough…
lobu-builder
Use when working inside a Lobu project generated by @lobu/cli or any repository centered on lobu.config.ts, AGENTS.md, agent prompt files, local skills, and evals. This skill helps a coding agent inspect the right files, make Lobu-native changes, keep the stack runnable, and validate semantics with chat tests and…
crm-ops
How to operate the Lobu funnel CRM — create and enrich leads, log interactions, advance funnel stages, open and update pilots, and produce the weekly digest. Use whenever the task touches the pipeline.
deliveroo-order
Turn collected lunch orders into a clean per-person order list for a human to place on Deliveroo. Use in step 2 of the lunch run, after orders are collected. The live menu is fetched automatically by the lobu-team-lunch-finalize reaction (via the Owletto Chrome extension) — this skill never places an order or touches…
self-motivation-corruption-system
系统性压力，机制驱动，持续输出.