Code Review
imbenrabi/Financial-Modeling-Prep-MCP-Server
Review a PR or working diff against this repo's intent layer (the AGENTS.md hierarchy), toolception pitfalls, and core invariants.
Compiles REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives.
Install Review Steering
$ npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dralgorhythm/claude-agentic-framework review-steering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dralgorhythm/claude-agentic-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/core-engineering/review-steering .claude/skills/review-steering && rm -rf skills-srcUse ~/.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/
Install the "review-steering" agent skill from https://github.com/dralgorhythm/claude-agentic-framework/tree/main/.claude/skills/core-engineering/review-steering into .claude/skills/review-steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-steering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dralgorhythm/claude-agentic-framework/tree/main/.claude/skills/core-engineering/review-steeringType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dralgorhythm/claude-agentic-framework review-steering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dralgorhythm/claude-agentic-framework.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/core-engineering/review-steering .agents/skills/review-steering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "review-steering" agent skill from https://github.com/dralgorhythm/claude-agentic-framework/tree/main/.claude/skills/core-engineering/review-steering into .agents/skills/review-steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-steering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dralgorhythm/claude-agentic-framework review-steering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dralgorhythm/claude-agentic-framework.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/core-engineering/review-steering .cursor/skills/review-steering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "review-steering" agent skill from https://github.com/dralgorhythm/claude-agentic-framework/tree/main/.claude/skills/core-engineering/review-steering into .cursor/skills/review-steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-steering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dralgorhythm/claude-agentic-framework.git --path .claude/skills/core-engineering/review-steering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dralgorhythm/claude-agentic-framework review-steering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dralgorhythm/claude-agentic-framework.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/core-engineering/review-steering .gemini/skills/review-steering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "review-steering" agent skill from https://github.com/dralgorhythm/claude-agentic-framework/tree/main/.claude/skills/core-engineering/review-steering into .gemini/skills/review-steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-steering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dralgorhythm/claude-agentic-framework review-steeringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dralgorhythm/claude-agentic-framework.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/core-engineering/review-steering .github/skills/review-steering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "review-steering" agent skill from https://github.com/dralgorhythm/claude-agentic-framework/tree/main/.claude/skills/core-engineering/review-steering into .github/skills/review-steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-steering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dralgorhythm/claude-agentic-framework review-steering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dralgorhythm/claude-agentic-framework.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/core-engineering/review-steering .opencode/skills/review-steering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "review-steering" agent skill from https://github.com/dralgorhythm/claude-agentic-framework/tree/main/.claude/skills/core-engineering/review-steering into .opencode/skills/review-steering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-steering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
review-steering- GitHub stars
- 125
- Token cost
- ~1.1k tokens
- SKILL.md length
- 503 words
- Files
- 4
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- None found
At a glance
Compiles REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives.
- Works in 8 steps: Read .claude/rules/code-quality.md —… → Read .claude/rules/security.md —… → Compile both into REVIEW.md as terse… → …
- Updating REVIEW.md
- SKILL.md covers Two Surfaces, Not One, Generation Workflow, Imperative Style, Not Prose and Refresh Discipline, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Review Steering is an agent skill from dralgorhythm/claude-agentic-framework. Compiles REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives. Use when creating or updating REVIEW.md, configuring or steering automated code review, or reconciling review instructions after rules change.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `evals/README.md`, `evals/evals.json` and `resources/review.template.md`).
It sits in Development, covering Translation, Code review and Agent instruction files. The repository describes itself as: A More Effective Agent Harness for Claude.
When your agent uses it
- Updating REVIEW.md
- Steering automated code review
- Reconciling review instructions after rules change
Example prompts
- “s managed Code Review service, translating this repo”
- “Use the review-steering skill to compile REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code…”
- “/review-steering”
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Read .claude/rules/code-quality.md — quality gates, SOLID/DRY musts, performance checklist.
- Read .claude/rules/security.md — security checklist, severity classification (block on Critical/High), CWE-reference convention.
- Compile both into REVIEW.md as terse reviewer imperatives — "flag X", "block on Y", "ignore Z" — never prose restatements of the rules.
- Keep it short: reviewers get REVIEW.md injected on every run, and every extra line dilutes the priority of the lines that matter.
- Add repo-specific invariants a generic reviewer cannot infer from a diff alone — artifact-naming conventions, enforcement-ladder…
- Confirm CLAUDE.md still states project context accurately; both surfaces depend on it being current.
- Scaffold from the bundled template and replace every placeholder before committing — see Resources below.
- Stamp the final line with <!-- rules-hash: -->, where is the output of cat .claude/rules/code-quality.md .claude/rules/security.md |…
What it can do on your machine
Read from SKILL.md and the folder at commit 6436a20. 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.
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
Review Steering loads about 1.1k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 503 words of instructions outside code blocks.
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
Without a licence we can't republish the file, so here is its outline and opening line. It has 503 words (~1,094 tokens).
“Anthropic's managed Code Review service and the local /code-review command are customized through exactly two files — nothing else steers them.”
- name
- review-steering
- metadata.category
- capability-uplift
Files
SKILL.md and 3 other files in .claude/skills/core-engineering/review-steering of dralgorhythm/claude-agentic-framework.
- SKILL.md
- evals/README.md
- evals/evals.json
- resources/review.template.md
Open the folder on GitHubat commit 6436a20
Compare with similar skills
Review Steering 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Review Steering this skilldralgorhythm/claude-agentic-framework | 125 | — | ~1.1k | Automated safety check: Pass | None | |
| Code Reviewimbenrabi/Financial-Modeling-Prep-MCP-Server | 150 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Shipmillionco/react-doctor | 15k | — | ~716 | Automated safety check: Pass | Custom licence | |
| Promptkitmicrosoft/PromptKit | 111 | — | ~420 | Automated safety check: Pass | MIT | |
| Megingiard Code Reviewstormpanda/megingiard | 154 | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| Ad ReviewCorridorTech/PoseCap | 224 | — | ~2.4k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Ship
millionco/react-doctor
Take the current branch from done-coding to merge-ready in one pass — review the diff against AGENTS.md, deslop, commit and push, open a PR using rule-validate's PR copy, then babysit until mergeable.
- Official
Promptkit
microsoft/PromptKit
PromptKit composition engine. An agent skill from microsoft/PromptKit.
Megingiard Code Review
stormpanda/megingiard
Conduct a thorough code review of the current Git branch or specific files in Megingiard.
Ad Review
CorridorTech/PoseCap
Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.
Fitness Functions
rshankras/claude-code-apple-skills
Write architecture fitness functions — deterministic tests that enforce a project's hard rules (module boundaries, offline guarantees, content contracts) from inside its own test target.
More from dralgorhythm/claude-agentic-framework
All 20 skills in this repoSwarm Coordination
dralgorhythm/claude-agentic-framework
Rules for several agents sharing one repository: an orchestrator tracks work in two tiers, workers write to scratch files, and every handoff leaves a pointer to an artifact.
Threat Modeling
dralgorhythm/claude-agentic-framework
Finds security threats in a design with a STRIDE pass per component, rates severity and records fixes, with extra checks for AI agent and tool risks.
Architecture Decision Record Writer
dralgorhythm/claude-agentic-framework
Writes Architecture Decision Records with title, status, context, decision, rationale and consequences for significant technical choices, kept short and numbered.
Codebase Health Auditor
dralgorhythm/claude-agentic-framework
Runs a user-invoked, swarm-style audit of a whole codebase for SOLID and DRY violations, code smells, complexity, dead code and pattern consistency, with a prioritized report.
Dependency Upgrade Protocol
dralgorhythm/claude-agentic-framework
Sequences safe dependency upgrades: read the changelog, verify the version exists upstream, pin it, and keep major bumps in separate commits behind a full gate run.
Designing Systems
dralgorhythm/claude-agentic-framework
Produces this framework's ADR and system-design artifacts from bundled templates with trade-off analysis.
Related
Categories
Questions about Review Steering
What does Review Steering do?
Compiles REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives. Review Steering is an agent skill from dralgorhythm/claude-agentic-framework.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives.
When should I use Review Steering?
Review Steering fits situations like: updating REVIEW.md; steering automated code review; reconciling review instructions after rules change.
How do I install Review Steering in Claude Code?
Run `npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a claude-code`. Or copy the skill folder (.claude/skills/core-engineering/review-steering in dralgorhythm/claude-agentic-framework) into .claude/skills/review-steering in your project. Claude Code loads it when a task matches its description.
How do I install Review Steering in Codex?
Run `npx skills add dralgorhythm/claude-agentic-framework --skill review-steering -a codex`. Or copy the skill folder (.claude/skills/core-engineering/review-steering in dralgorhythm/claude-agentic-framework) into .agents/skills/review-steering in your project. Codex loads it when a task matches its description.
Can I use Review Steering 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 dralgorhythm/claude-agentic-framework --skill review-steering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-steering, .gemini/skills/review-steering, .github/skills/review-steering and .opencode/skills/review-steering in your project.
What does Review Steering need to run?
SKILL.md names no scripts, command-line tools or credentials: Review Steering is instructions for the agent only.
Does Review Steering 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 Review Steering 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 Review Steering use?
No licence was found for Review Steering or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Review Steering use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 Review Steering?
Skills that share tags, products or a category with Review Steering: Code Review (imbenrabi/Financial-Modeling-Prep-MCP-Server, 150 stars), Ship (millionco/react-doctor, 15k stars), Promptkit (microsoft/PromptKit, 111 stars) and Megingiard Code Review (stormpanda/megingiard, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Review Steering?
dralgorhythm (a GitHub user) maintains it in dralgorhythm/claude-agentic-framework, which has 125 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on July 24, 2026.
Source: dralgorhythm/claude-agentic-framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.