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 fabioc-aloha/Alex_Skill_Mall --skill deep-reviewgit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/fabioc-aloha/alex_skill_mall/deep-review)<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/deep-review"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/deep-review/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/fabioc-aloha/alex_skill_mall/deep-review"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/deep-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.01322 |
| Opus 5.5 | $0.00022 | $0.00529 |
| Sonnet 5.5 | $0.00011 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
deep-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 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Review
Perform thorough code review using three perspectives with opposing mindsets. Their disagreement surfaces issues; their agreement signals confidence.
When to Use
- Architectural changes, multi-file refactors, or security-sensitive code
- PRs that are too important for single-pass review
- When you suspect confirmation bias in a standard review
- High-stakes merges where the cost of a missed issue is high
When NOT to Use
- Routine single-file edits (use standard
code-reviewskill) - Documentation-only PRs
- Formatting/linting changes
The Three Perspectives
| Agent | Mindset | Question | Owns |
|---|---|---|---|
| Advocate | "Why is this correct?" | Trust boundaries, design rationale, false-positive defense | Correctness defense |
| Skeptic | "How can I break this?" | Bugs, edge cases, code smells that indicate bugs | Correctness attack |
| Architect | "Is this the right direction?" | System impact, scope, structural smells, tech debt | Direction |
Workflow
Phase 1: Gather Context
- Identify the changes — PR diff, local changes, or specific files
- Collect context — related files, tests, recent history of changed modules
- Note observations — anything unusual before analysis begins
Phase 2: Parallel Analysis
Run all three perspectives independently. Each sees the same context but asks different questions.
Advocate Analysis
- What problem does this solve?
- What design decisions are intentional (not accidental)?
- Where are the trust boundaries correctly placed?
- What would break if we rejected this PR?
- Defend against false-positive concerns raised by Skeptic
Skeptic Analysis
- What inputs could break this? (null, empty, overflow, concurrent, malicious)
- What error paths are unhandled?
- What assumptions are undocumented?
- What would a fuzzer find?
- What code smells indicate deeper bugs? (naming lies, magic numbers, commented-out code)
- What works in tests but would fail in production?
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 · 161 lines · 54 tokens per session scan A e7149ab17732
deep-review is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (5 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 1,322 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
refactor
Analyze code for SOLID violations and suggest targeted improvements.
cva-analysis
Systematic abstraction discovery using Commonality Variability Analysis. Build matrix of what varies vs what's constant, then let patterns emerge. Prevents wrong abstractions by deferring pattern selection until requirements are analyzed. Use when facing multiple similar requirements and need to discover natural…
memory-enhancement
Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still valid. Use when you say "add a citation", "verify this memory's code refs", "check memory health". Do NOT use for searching or creating…
panning-for-gold
Triage raw unstructured input (transcripts, brain dumps) into evaluated thread inventories and a synthesized gold-found file. Four phases: front-gate, extract, evaluate, synthesize. Use when you say "pan for gold", "triage transcript", "synthesize gold-found", or hand it a voice transcript or brain dump. Do NOT use…
prompt-engineer
Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors. Use when you say "optimize this prompt", "improve this system prompt", or "review my agent prompt".
context-gather
Gather comprehensive context from Serena memory, Context7 docs, DeepWiki, and web sources before planning or implementation. Searches across all knowledge tiers and returns a focused summary ending in a CONTEXTLOADED marker that this skill scans to skip a repeat fetch in the same conversation. Use when you say "gather…