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/dvnghiem/flowdeck/code-reviewnpx skills add DVNghiem/FlowDeck --skill code-reviewgit clone --depth 1 https://github.com/DVNghiem/FlowDeckWhat 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 | $0.00025 | $0.00654 |
| Opus 5 | $0.00013 | $0.00327 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Skill
Finds real problems before they reach production. Reviews only changed code, reports only confirmed issues, and provides actionable fixes.
When to Activate
Activate when:
- You just wrote or modified code
- A PR is ready for review
- You want a final check before pushing
Core Principles
- Report only confirmed issues — 80%+ confidence before flagging
- Severity-ranked output: Critical → High → Medium → Pass
- Actionable fixes: every finding includes a specific remediation
- No style nitpicks unless they mask bugs
Workflow
- Run
git diffor read specified files - Read full file context (not just the diff)
- Trace call sites — who calls these functions?
- Apply security checklist first
- Apply quality checklist
- Report by severity
Security Checklist — CRITICAL
SQL Injection:
// ❌ CRITICAL
const q = `SELECT * FROM users WHERE id = '${userId}'`;
// ✅ Parameterized
const q = db.query('SELECT * FROM users WHERE id = ?', [userId]);
XSS:
<!-- ❌ CRITICAL -->
element.innerHTML = userInput;
<!-- ✅ -->
element.textContent = userInput;
Hardcoded credentials:
// ❌ CRITICAL
const SECRET = "abc123hardcoded";
// ✅
const SECRET = process.env.API_SECRET;
Path traversal:
// ❌ CRITICAL
fs.readFile(`./uploads/${filename}`);
// ✅
fs.readFile(path.join('./uploads', path.basename(filename)));
Quality Checklist — HIGH
- Functions over 50 lines → extract
- Nesting deeper than 3 levels → extract guard clauses
- Empty or silent catch blocks → log and rethrow
- Dead code (defined but never called) → remove
Performance — MEDIUM
- N+1 queries: database call inside a loop
- Missing pagination on list endpoints
- Synchronous I/O in hot paths
Best Practices — LOW
- Inconsistent naming within a file
- Missing JSDoc on public functions
console.logleft in production code
Output Format
## Code Review Report
### 🔴 CRITICAL (must fix before merge)
| # | File | Line | Issue | Fix |
|---|------|------|-------|-----|
| 1 | auth.ts | 42 | SQL injection | Use parameterized query |
### 🟠 HIGH (fix before merge)
| # | File | Line | Issue | Fix |
|---|------|------|-------|-----|
### 🟡 MEDIUM (fix in follow-up)
| # | File | Line | Issue | Fix |
|---|------|------|-------|-----|
### ✅ PASS
- Auth middleware: present on all protected routes
- Input validation: correct at all boundaries
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 · 109 lines · 25 tokens per session scan A dc59f559268e
code-review is a skill published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 13d ago), licensed MIT. It adds 25 tokens to every session and 654 once invoked, about $0.0001 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
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.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
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.
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.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.