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 skills add DVNghiem/FlowDeck --skill research-firstgit clone --depth 1 https://github.com/DVNghiem/FlowDeckWrote 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/skills/dvnghiem/flowdeck/research-first)<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/research-first"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/research-first/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/research-first"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/research-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 238 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00024 | $0.02962 |
| Opus 5.5 | $0.00010 | $0.01185 |
| Sonnet 5.5 | $0.00005 | $0.00592 |
| Haiku 4.5 | $0.00002 | $0.00296 |
Grade A, and why
research-first 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 1mo 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research-first — Research Hierarchy
Enforces a strict research-first workflow before any implementation. Research in order of proximity: codebase first, structured docs second, web third, registries last.
Trigger
Use this skill when:
- About to write any new function, module, or integration
- Unsure of an API signature, behavior, or pattern
- Creating utilities, helpers, or abstractions
- Evaluating whether to add a dependency
- Debugging an issue in unfamiliar code
The Four-Level Hierarchy
┌─────────────────────────────────────────────────────────────┐
│ RESEARCH HIERARCHY │
├─────────────────────────────────────────────────────────────┤
│ LEVEL 1: CODEBASE │
│ ┌─────────────┐ ┌─────────────────┐ │
│ │ fdx-graph │ │ grep.app │ │
│ │ (AST graph) │ │ (code search) │ │
│ └─────────────┘ └─────────────────┘ │
│ When: Need patterns, examples, or existing implementations │
│ Escalate: If codebase has no relevant code │
├─────────────────────────────────────────────────────────────┤
│ LEVEL 2: STRUCTURED DOCS │
│ ┌─────────────────┐ │
│ │ Context7 MCP │ │
│ │ (library docs) │ │
│ └─────────────────┘ │
│ When: Need accurate API signatures and usage │
│ Escalate: If library not indexed or docs incomplete │
├─────────────────────────────────────────────────────────────┤
│ LEVEL 3: WEB SEARCH │
│ ┌─────────────┐ ┌─────────────┐ │
│ │ Exa MCP │ │ Web fetch │ │
│ │ (semantic) │ │ (direct) │ │
│ └─────────────┘ └─────────────┘ │
│ When: Level 1-2 insufficient or library unfamiliar │
│ Escalate: If no authoritative source found │
├─────────────────────────────────────────────────────────────┤
│ LEVEL 4: PACKAGE REGISTRIES │
│ ┌─────────────┐ ┌─────────────┐ │
│ │ npm / PyPI │ │ GitHub │ │
│ │ (search) │ │ (packages) │ │
│ └─────────────┘ └─────────────┘ │
│ When: Need to verify existence of utility / alternative │
│ Escalate: Only if nothing suitable exists │
└─────────────────────────────────────────────────────────────┘
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.
- 1mo ago First seen · 346 lines · 24 tokens per session scan A 6da3d8840fdb
research-first is a skill published in the GitHub repository DVNghiem/FlowDeck (36 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 2,962 once invoked, about $0.0001 per session on Opus 5.5. 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
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
deepwork
High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.