Borrowing it
Nothing to install: this file belongs to corespan/aistudio-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/corespan/aistudio-app/master/.claude/skills/tech-lead-code-review/SKILL.mdgit 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/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/corespan/aistudio-app/tech-lead-code-review"><img src="https://agentmods.dev/badge/skills/corespan/aistudio-app/tech-lead-code-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 | $0.00214 | $0.01419 |
| Opus 5.5 | $0.00086 | $0.00568 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 yesterday), licensed Apache-2.0. It adds 214 tokens to every session and 1,419 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…