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/conectlens/lenserfight/deep-code-reviewernpx skills add conectlens/lenserfight --skill deep-code-reviewergit clone --depth 1 https://github.com/conectlens/lenserfightWrote 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/conectlens/lenserfight/deep-code-reviewer)<a href="https://agentmods.dev/skills/conectlens/lenserfight/deep-code-reviewer"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/deep-code-reviewer.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.01026 |
| Opus 5 | $0.00048 | $0.00513 |
| Sonnet 5 | $0.00019 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
deep-code-reviewer 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Code Reviewer
Perform review as an auditor, not as a summarizer. Prioritize findings that can cause incorrect behavior, operational pain, or expensive future changes.
Quick Start
- Establish scope before judging details.
- Inspect surrounding code, not just the diff or pasted snippet.
- Trace data flow, control flow, state transitions, and failure paths.
- Produce findings ordered by severity with concrete file references.
- Keep summaries brief and secondary to the findings.
Review Workflow
1. Build Context
Read enough code to understand:
- Entry points and callers
- State ownership and mutation boundaries
- Invariants that must always hold
- External dependencies: databases, queues, caches, RPCs, files, clocks, feature flags
- Existing tests and what they do not cover
If the change touches a framework or subsystem with non-obvious behavior, read the local docs or implementation that defines the contract before concluding.
2. Hunt for High-Impact Failures First
Check for:
- Incorrectness: broken invariants, off-by-one logic, missing validation, bad error handling, partial updates
- Concurrency hazards: races, duplicate work, lost updates, stale reads, deadlocks, non-atomic sequences
- Security flaws: authorization gaps, trust-boundary violations, secret leakage, injection vectors
- Data integrity issues: transaction gaps, mismatched schemas, silent truncation, incompatible migrations
- Performance cliffs: N+1 queries, unnecessary allocations, hot-loop work, unbounded retries, lock contention
- Type-safety holes: unsafe casts, invalid narrowing, nil/null handling gaps, unsound generics, unchecked parsing
- Operational risks: weak observability, bad retry semantics, missing idempotency, unsafe rollout assumptions
3. Evaluate Architecture and Design
Judge whether the design makes future failures likely even if the current code appears correct.
Look for:
- Responsibilities split across the wrong boundaries
- APIs that hide important invariants or encourage misuse
- Tight coupling to volatile details
- Configuration or feature-flag logic that creates invalid states
- Missing abstractions where duplication is already diverging
- Premature abstractions that make correctness harder to reason about
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 111 lines · 95 tokens per session scan A 99517ba57146
deep-code-reviewer is a skill published in the GitHub repository conectlens/lenserfight (19 stars, last pushed 25d ago), licensed MIT. It adds 95 tokens to every session and 1,026 once invoked, about $0.0005 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
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
nanoresearch-ideation
Search academic literature and generate research hypotheses.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
auto-experiment
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENTPLAN.md, routes mechanism family inline (Phase 1.5), implements experiment code, deploys to GPU, and collects initial results. Use when user says "implement experiments", "experiment", "deploy the plan", or has an experiment plan ready to…
crosscoder-learning
Use this skill when working with sparse autoencoders (SAEs), crosscoders, dictionary learning on neural network activations, training SAEs/crosscoders from scratch, loading pretrained dictionaries, caching model activations, or comparing model internals across fine-tuned model pairs using the dictionarylearning /…