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/research-workflownpx skills add spytensor/openmozi --skill research-workflowgit 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 | $0.00059 | $0.00516 |
| Opus 5 | $0.00030 | $0.00258 |
| Sonnet 5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
research-workflow 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.
What it actually says
Research Workflow
How to Execute
- Decompose: Break the question into 2-5 sub-questions that can be researched independently.
- Search: Use web_search for each sub-question. Parallelize independent searches.
- Cross-verify: Check claims from multiple sources. Flag conflicting information.
- Synthesize: Combine findings into a structured answer with citations.
- Qualify: State confidence level and note gaps in available information.
Rules
- Never rely on training data alone for factual claims — always verify with web_search.
- Prefer primary sources (official docs, papers, announcements) over secondary ones.
- When sources conflict, present both sides and explain the discrepancy.
- Include dates for time-sensitive information.
- Clearly separate facts from your analysis or interpretation.
Freshness Self-Check (mandatory when the request says "latest", "recent", "最新", "近期", or implies now)
- Anchor: read the current date from the runtime time facts — that is "now", not your training data.
- Query with recency: include the current year (and month if relevant) in search queries; prefer provider recency filters when available.
- Date every source: extract each result's publication date. A result without a discoverable date is weak evidence for a "latest" claim.
- Compare before claiming: if the newest source you found is older than the request implies (e.g. a year-old report for a "latest report" request), say so explicitly — "the newest I could verify is X from " — instead of presenting it as current.
- If search is unavailable or returns nothing recent, state plainly what you could not verify. Never fill the gap from training data without labeling it as such.
Pitfalls
- Presenting training data as verified fact
- Citing a single source without cross-checking
- Omitting publication dates on time-sensitive topics
- Mixing opinion with established fact
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 · 42 lines · 59 tokens per session scan A e789ac310b5e
research-workflow is a skill published in the GitHub repository spytensor/openmozi (210 stars, last pushed 26d ago), licensed MIT. It adds 59 tokens to every session and 516 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…
lobu
Use Lobu MCP for shared, permission-aware company context, durable organizational memory, and governed actions. Trigger when the user asks what the organization knows, needs context from connected company systems, wants to preserve a durable fact or decision, or needs to discover and use Lobu SDK capabilities.