Agent skill

Supercheck Code Review

by supercheck-io in supercheck-io/supercheck

Review Supercheck staged, unstaged, commit, branch, or pull-request changes for correctness, regressions, security, tenancy, architecture, tests, docs, licensing, and commit/merge/release readiness.

AGPL-3.0Auto-check passedDevelopment

Install Supercheck Code Review

skills CLI
$ npx skills add supercheck-io/supercheck --skill supercheck-code-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install supercheck-io/supercheck supercheck-code-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/supercheck-io/supercheck.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-review .claude/skills/supercheck-code-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
supercheck-code-review
GitHub stars
215
Token cost
~1k tokens
SKILL.md length
357 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Review Supercheck staged, unstaged, commit, branch, or pull-request changes for correctness, regressions, security, tenancy, architecture, tests, docs, licensing, and commit/merge/release readiness.

  • Tasks that involve Code review
  • SKILL.md covers Establish scope, Trace behavior, Critical review areas and Findings format, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Feature launches and release readiness

What it does

Supercheck Code Review is an agent skill from supercheck-io/supercheck. Review Supercheck staged, unstaged, commit, branch, or pull-request changes for correctness, regressions, security, tenancy, architecture, tests, docs, licensing, and commit/merge/release readiness.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review, Feature launches and release readiness and Pull requests. The repository describes itself as: Open-Source Testing, Monitoring, and AI SRE — as Code. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Code review
  • Tasks that involve Feature launches and release readiness
  • Tasks that involve Pull requests

Example prompts

  • “/supercheck-code-review”

What it can do on your machine

Read from SKILL.md and the folder at commit 0c077d0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Supercheck Code Review loads about 1k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 357 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from supercheck-io/supercheck at commit 0c077d0, republished under its AGPL-3.0 licence (© supercheck-io). 357 words, ~1,007 tokens.

Download SKILL.mdSave it as .claude/skills/supercheck-code-review/SKILL.md (or your agent's skills folder).
name
supercheck-code-review
description
Review Supercheck staged, unstaged, commit, branch, or pull-request changes for correctness, regressions, security, tenancy, architecture, tests, docs, licensing, and commit/merge/release readiness.

Supercheck code review

Use every domain skill touched by the diff. Review is read-only unless the user also asks to fix findings.

Establish scope

  • Identify repositories, branch/base, commits, staged/unstaged/untracked files, submodules, generated outputs, and existing unrelated changes.
  • Review the effective combined change, not only staged or unstaged fragments when both exist.
  • Classify each file as architecture/data, auth/security, API/action, UI/hooks, execution/worker, monitoring, storage, SRE, deployment, testing/docs, CLI, recorder, billing, or another integration.

Trace behavior

For each changed contract, follow:

mermaid
flowchart LR
  CALLER[Caller/user input] --> TRUST[Auth and validation]
  TRUST --> LOGIC[Business logic]
  LOGIC --> STATE[DB, cache, queue, object, provider]
  STATE --> CONSUMER[Worker/UI/CLI/integration]
  CONSUMER --> TEST[Tests and docs]
  • A diff that looks correct locally can still break a caller, worker, old deployment, CLI, extension, migration, or retry path.
  • Treat reported findings as hypotheses. Confirm through current source, call paths, tests, and runtime contracts before recommending changes.
  • Do not convert intentional hardening into a finding merely because it is stricter than generic guidance.

Critical review areas

  • Authentication mechanism and exact RBAC resource/action for cookie, bearer, trigger, admin, and public routes.
  • Organization/project ownership on reads, writes, joins, cache keys, streams, objects, queue jobs, and provider identities.
  • Zod/input bounds, uploads, HTML/browser messages, SSRF/redirect/DNS behavior, webhook signatures, and output allowlists.
  • Secret encryption/redaction and absence from client data, config, queues, logs, errors, model prompts, and artifacts.
  • Migration existing-data safety, constraints/indexes, lock duration, destructive operations, rollback/recovery, and version skew.
  • Queue payload parity, atomic capacity, retries/idempotency, duplicate delivery, cancellation, terminal cleanup, and worker loss.
  • React server/client boundary, query-key/invalidation parity, stale data, accessibility, error/loading/empty behavior.
  • External effects: timeout, retry safety, idempotency, cancellation, billing/usage exactly-once behavior, and provider reconciliation.
  • Deployment: immutable versions, secret handling, gVisor/network/namespace isolation, resource ceilings, autoscaling, health, and destructive blast radius.
  • CLI/recorder public compatibility and AGPL versus Apache/third-party NOTICE obligations.
Show full SKILL.md (93 more words)Show less

Findings format

  • Order by severity: critical/security/data loss, functional regression, reliability/performance, maintainability, suggestion.
  • Give exact file/line, concrete failure scenario, affected users/system, and smallest safe correction.
  • Avoid style-only noise unless repository tooling enforces it or it materially obscures correctness.
  • Record important investigated claims that are not defects so reviewers understand intentional behavior.

Verification and decision

mermaid
flowchart TD
  REVIEW[Source/call paths reviewed] --> CHECK{Relevant checks pass?}
  CHECK -->|no| BLOCK[Not commit-ready]
  CHECK -->|yes| CLEAN{State and docs clean?}
  CLEAN -->|no| BLOCK
  CLEAN -->|yes| COMMIT[Commit-ready]
  COMMIT --> CI[Required CI/review]
  CI --> ACCEPT[Browser/provider/deployment acceptance]
  ACCEPT --> RELEASE[Release-ready]
  • Run proportionate focused checks and broaden for shared/high-risk contracts.
  • Confirm whitespace/diff checks, package contents, ignored/generated files, migrations, and docs/skills parity.
  • Separate commit readiness from merge and release readiness.
  • An unavailable browser/provider/production check is a disclosed acceptance boundary, never a pass.

© supercheck-io, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/code-review of supercheck-io/supercheck.

Open the folder on GitHubat commit 0c077d0

Compare with similar skills

Supercheck Code Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Supercheck Code Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Supercheck Code Review this skillsupercheck-io/supercheck215—~1kAutomated safety check: PassAGPL-3.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
WooCommerce Code Reviewwoocommerce/woocommerce11k3 repos~1.1kAutomated safety check: PassCustom licence
Open Code Review CLIalibaba/open-code-review44k—~3.1kAutomated safety check: PassApache-2.0
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    44k GitHub stars~3.1k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Code Review

    flutter/flutter

    Performs a comprehensive, multi-step code review of pull requests or local code changes, using iterative refinement (generation, critique, synthesis) to ensure high-quality, actionable feedback.

    179k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

More from supercheck-io/supercheck

All 12 skills in this repo
  • Supercheck Security Auth

    supercheck-io/supercheck

    Work on Supercheck authentication, RBAC, tenant isolation, sessions, API and trigger keys, invitations, project membership, project variables, OAuth, super-admin behavior, SSRF, or…

    215 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Supercheck Architecture

    supercheck-io/supercheck

    Work on Supercheck system architecture, Next.js routes and actions, React data hooks, Drizzle schemas and migrations, app-worker boundaries, or cross-package contracts.

    215 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Supercheck Data Storage

    supercheck-io/supercheck

    Work on Supercheck PostgreSQL data, S3 or MinIO artifacts, signed URLs and asset proxying, retention cleanup, dashboard/report queries, exports, or audit logging.

    215 GitHub stars~942 tokensUpdated today
    Auto-check passed
  • Supercheck Execution Engine

    supercheck-io/supercheck

    Work on Supercheck BullMQ queues, schedulers, capacity management, Playwright or k6 execution, monitors, dynamic locations, cancellation, Redis, Kubernetes Jobs, gVisor, or app-worker execution…

    215 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Supercheck Feature Implementation

    supercheck-io/supercheck

    Implement a new or changed Supercheck feature end to end across schema, auth/RBAC, services, routes/actions, UI, queues/workers, CLI/recorder, tests, docs, and deployment contracts.

    215 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Supercheck Infrastructure Deployment

    supercheck-io/supercheck

    Work on Supercheck Docker Compose, K3s, Kubernetes manifests, gVisor, OpenTofu/Hetzner, secrets, external services, autoscaling, backups, disaster recovery, DNS/TLS, or production deployment.

    215 GitHub stars~1.4k tokensUpdated today
    Auto-check: notes

Categories

Questions about Supercheck Code Review

What does Supercheck Code Review do?

Review Supercheck staged, unstaged, commit, branch, or pull-request changes for correctness, regressions, security, tenancy, architecture, tests, docs, licensing, and commit/merge/release readiness. Supercheck Code Review is an agent skill from supercheck-io/supercheck. Review Supercheck staged, unstaged, commit, branch, or pull-request changes for correctness, regressions, security, tenancy, architecture, tests, docs, licensing, and commit/merge/release readiness.

When should I use Supercheck Code Review?

Supercheck Code Review fits situations like: tasks that involve Code review; tasks that involve Feature launches and release readiness; tasks that involve Pull requests.

How do I install Supercheck Code Review in Claude Code?

Run `npx skills add supercheck-io/supercheck --skill supercheck-code-review -a claude-code`. Or copy the skill folder (.agents/skills/code-review in supercheck-io/supercheck) into .claude/skills/supercheck-code-review in your project. Claude Code loads it when a task matches its description.

How do I install Supercheck Code Review in Codex?

Run `npx skills add supercheck-io/supercheck --skill supercheck-code-review -a codex`. Or copy the skill folder (.agents/skills/code-review in supercheck-io/supercheck) into .agents/skills/supercheck-code-review in your project. Codex loads it when a task matches its description.

Can I use Supercheck Code Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add supercheck-io/supercheck --skill supercheck-code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/supercheck-code-review, .gemini/skills/supercheck-code-review, .github/skills/supercheck-code-review and .opencode/skills/supercheck-code-review in your project.

What does Supercheck Code Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Supercheck Code Review is instructions for the agent only.

Does Supercheck Code Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Supercheck Code Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Supercheck Code Review use?

Supercheck Code Review is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Supercheck Code Review use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Supercheck Code Review?

Skills that share tags, products or a category with Supercheck Code Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars), WooCommerce Code Review (woocommerce/woocommerce, 11k stars) and Open Code Review CLI (alibaba/open-code-review, 44k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Supercheck Code Review?

supercheck-io (a GitHub organization) maintains it in supercheck-io/supercheck, which has 215 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

Source: supercheck-io/supercheck on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.