New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agentic Review

by dxos in dxos/dxos

Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet…

Custom licenceAuto-check passedDevelopment

Install Agentic Review

skills CLI
$ npx skills add dxos/dxos --skill agentic-review -a claude-code

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

GitHub CLI
$ gh skill install dxos/dxos agentic-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/dxos/dxos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agentic-review .claude/skills/agentic-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
agentic-review
GitHub stars
525
Token cost
~4.4k tokens
SKILL.md length
2,097 words
Files
40 (incl. scripts)
Skills in repo
41
Repo updated
First seen
Licence
Custom licence

At a glance

Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet…

  • Works in 6 steps: Prepare → Spawn one Sonnet subagent per group → Finalize → …
  • Asked to run the agentic review
  • SKILL.md covers Layout, Workflow, PR mode (fast review + CI) and Authoring a rule, plus 1 more section
  • Runs TypeScript scripts from its folder; calls bun and node; needs TYPESAFE_API_KEY

What it does

Agentic Review is an agent skill from dxos/dxos. Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet subagent per group, then finalize the merged diagnostics into a single REVIEW.md. Use when asked to run the agentic review, list unresolved review issues, review a branch/PR against the repo's .mdl rules, or check a diff for known anti-patterns. For the built-in bug/quality passes use /code-review instead. A cheaper…

Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 41 other files, including scripts (for example `lib/diagnostics.ts`, `lib/discover.ts` and `lib/frontmatter.ts`).

It sits in Development, covering Subagents, Pull requests and Code review. The repository describes itself as: TypeScript implementation of the DXOS protocols, SDK, toolchain and Composer.

When your agent uses it

  • Asked to run the agentic review
  • List unresolved review issues
  • Review a branch/PR against the repos .mdl rules
  • Check a diff for known anti-patterns

Example prompts

  • “/agentic-review”

Requirements

  • Node.js
  • A credential in TYPESAFE_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Prepare
  2. Spawn one Sonnet subagent per group
  3. Finalize
  4. Report
  5. Address issues (the index)
  6. List unresolved issues

What it can do on your machine

Read from SKILL.md and the folder at commit 2e6b92a. 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

    Ships 1 file in scripts/ (TypeScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • bun
    • node

    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 these keys or tokens, usually read from environment variables:

    • TYPESAFE_API_KEY

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

Context cost

Agentic Review loads about 4.4k tokens when it runs. Until then it costs about 205 tokens; SKILL.md has 2,097 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~205
When it runs · the whole SKILL.md, loaded when a task matches
~4.4k

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,097 words (~4,443 tokens).

“A harness that checks the tree against rule blocks defined in .mdl files — semantic rules a linter can't express ("prefer subscribing to events over polling in tests"). Each rule is applied by a focused LLM subagent, scoped to one…”

— opening of SKILL.md by dxos, Custom licence
name
agentic-review

Read the full SKILL.md on GitHub

Files

SKILL.md and 39 other files (scripts) in .agents/skills/agentic-review of dxos/dxos.

  • SKILL.md
  • lib/diagnostics.ts
  • lib/discover.ts
  • lib/frontmatter.ts
  • lib/git.ts
  • lib/mdl.ts
  • lib/pr-check.test.ts
  • lib/pr-check.ts
  • lib/resolution.ts
  • lib/review-doc.test.ts
  • lib/review-doc.ts
  • lib/store.ts
  • lib/supersede.test.ts
  • lib/supersede.ts
  • lib/system-one/budget.ts
  • lib/system-one/checker.ts
  • lib/system-one/client.ts
  • lib/system-one/fetchers.ts
  • lib/system-one/questions.ts
  • … and 21 more

Open the folder on GitHubat commit 2e6b92a

Compare with similar skills

Agentic 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.

Agentic Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agentic Review this skilldxos/dxos525—~4.4kAutomated safety check: PassCustom licence
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0
Cherry Studio PR ReviewCherryHQ/cherry-studio52k—~3.9kAutomated safety check: PassAGPL-3.0
PR Reviewjaemk/self_update961—~1.5kAutomated safety check: NotesMIT
cmux Pre-Merge Reviewmanaflow-ai/cmux28k—~681Automated safety check: PassCustom licence
PR Reviewjaemk/cached2.1k—~2.5kAutomated safety check: NotesMIT

Similar skills

  • GitHub Review Iteration

    prisma/orm

    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

  • Cherry Studio PR Review

    CherryHQ/cherry-studio

    Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.

    52k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed

  • PR Review

    jaemk/self_update

    Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/self_update.

    961 GitHub stars~1.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

  • cmux Pre-Merge Review

    manaflow-ai/cmux

    Reviews agent-written changes before merge with a review subagent and evidence-backed findings, plus a fuller adversarial protocol for security and data-loss risk.

    28k GitHub stars~681 tokensUpdated today
    DevelopmentAuto-check passed

  • PR Review

    jaemk/cached

    Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/cached.

    2.1k GitHub stars~2.5k tokensUpdated 8 days ago
    DevelopmentAuto-check: notes

More from dxos/dxos

All 41 skills in this repo

  • Composer Forensics

    dxos/dxos

    Forensically inspect and repair Composer browser profiles — offline (Chrome OPFS / SQLite extract) or live via /recovery.html debug port.

    525 GitHub stars~3.1k tokensUpdated today
    Auto-check passed

  • Migrate Oxfmt

    dxos/dxos

    Guide for migrating a project from Prettier or Biome to Oxfmt.

    525 GitHub starsUsed in 3 repos~2.2k tokens
    Auto-check passed

  • Moon

    dxos/dxos

    This skill should be used when the user asks to "configure moon", "set up moonrepo", "create moon tasks", "run moon commands", "configure moon workspace", "add moon project", "moon ci setup", "moon…

    525 GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Subduction Policy

    dxos/dxos

    Reference for SubductionPolicy (the four hooks authorizeConnect, authorizeFetch, authorizePut, filterAuthorizedFetch passed via Subduction.hydrate(..., policy) or new Repo({ subductionPolicy })).

    525 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Autocue

    dxos/dxos

    Record a demo of the running app that the agent drives itself — a .mdl QA test or an ad-hoc walkthrough — as a captioned .webm (or a screenshot), trimmed of dead air and ready to attach.

    525 GitHub stars~12k tokensUpdated today
    Auto-check passed

  • 1password

    dxos/dxos

    Get a credential (API key, token, password, certificate) from 1Password with the op CLI — only when OPSERVICEACCOUNTTOKEN is set (the cloud sandbox); in a local session never run op.

    525 GitHub stars~1k tokensUpdated today
    Auto-check: notes

Categories

Questions about Agentic Review

What does Agentic Review do?

Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet…. Agentic Review is an agent skill from dxos/dxos.md.

When should I use Agentic Review?

Agentic Review fits situations like: asked to run the agentic review; list unresolved review issues; review a branch/PR against the repos .mdl rules; check a diff for known anti-patterns.

How do I install Agentic Review in Claude Code?

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

How do I install Agentic Review in Codex?

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

Can I use Agentic 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 dxos/dxos --skill agentic-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/agentic-review, .gemini/skills/agentic-review, .github/skills/agentic-review and .opencode/skills/agentic-review in your project.

What does Agentic Review need to run?

Going by SKILL.md and its folder, Agentic Review needs TypeScript for the scripts in its folder, the command-line tools its instructions call (bun and node) and credentials named TYPESAFE_API_KEY. Our summary lists: Node.js; A credential in TYPESAFE_API_KEY.

Does Agentic 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 Agentic 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Agentic Review use?

Agentic Review has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Agentic Review use?

About 4.4k tokens (SKILL.md is roughly 18k 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 Agentic Review?

Skills that share tags, products or a category with Agentic Review: GitHub Review Iteration (prisma/orm, 48k stars), Cherry Studio PR Review (CherryHQ/cherry-studio, 52k stars), PR Review (jaemk/self_update, 961 stars) and cmux Pre-Merge Review (manaflow-ai/cmux, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agentic Review?

dxos (a GitHub organization) maintains it in dxos/dxos, which has 525 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 9, 2026.

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