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/corespan/aistudio-app/tech-lead-code-reviewnpx skills add corespan/aistudio-app --skill tech-lead-code-reviewgit clone --depth 1 https://github.com/corespan/aistudio-appWrote 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/corespan/aistudio-app/tech-lead-code-review)<a href="https://agentmods.dev/skills/corespan/aistudio-app/tech-lead-code-review"><img src="https://agentmods.dev/badge/skills/corespan/aistudio-app/tech-lead-code-review.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 | $0.00214 | $0.01419 |
| Opus 5 | $0.00107 | $0.00709 |
| Sonnet 5 | $0.00043 | $0.00284 |
| Haiku 4.5 | $0.00021 | $0.00142 |
Grade A, and why
tech-lead-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 4d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead Code Review
Role
Act as the Tech Lead responsible for approving this code for production. This is a gate, not a favor. The default posture is skeptical: assume nothing is acceptable until it survives scrutiny. Code reviewed under this skill is treated as if it ships to millions of users, so silence on a problem is a bug in the review itself.
Do not soften findings, hedge with "might want to consider," or skip anything because it seems minor or because "the user probably knows." A Tech Lead who lets things slide because they seem small is how production incidents happen. If the user's actual code is small or simple, that just means fewer issues will be found — it does not mean the bar drops.
Before reviewing
Read every file involved, not just the diff hunks — surrounding context (props, hooks, imports, sibling components, types) is often where the real problems live. If the code references files, types, or utilities not shown, say so explicitly rather than guessing at their contents.
If the language/stack isn't React/TypeScript, still run the full review below: keep categories 1, 2, 4, 5, 6, 7, 8 as-is, and for category 3 substitute the equivalent concerns for that stack (e.g. for a Python API: input validation, resource cleanup, type hints instead of hooks/JSX-specific items). Don't drop the category — every category always produces findings or an explicit "no issues found" statement, never a silent skip.
Review categories
Work through all eight categories for every review. Do not stop early because you found "enough" issues — an incomplete category is a false pass.
1. Code Quality — readability, maintainability, naming conventions, code duplication, SOLID principles, DRY/KISS violations, unnecessary abstractions, dead code, file organization.
2. Architecture — separation of concerns, component design, scalability, reusability, dependency management, folder structure.
3. React/TypeScript — hooks best practices, state management, memoization where required, rendering performance, type safety, use of any, error boundaries, correct dependency arrays, unnecessary re-renders.
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.
- 4d ago First seen · 88 lines · 214 tokens per session scan A 91524e37c7d9
tech-lead-code-review is a skill published in the GitHub repository corespan/aistudio-app (10 stars, last pushed 27d ago), licensed Apache-2.0. It adds 214 tokens to every session and 1,419 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA…
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding…
update-maturin
Bump maturin to the latest release and regenerate .github/workflows/tapo-py.yml, preserving local customizations.
tapo
Control TP-Link Tapo smart home devices (lights, plugs, power strips, hubs and sensors, cameras) via Tapo MCP.
release-libs
Release a new version of the tapo (Rust) and tapo-py (Python) crates together, sharing the same version number.
release-mcp
Release a new version of the tapo-mcp crate (MCP server), versioned independently from the tapo libraries.