How do I install the Code Review Orchestrator skill?

Run npx skillmds@latest add tomevault-io/code-review-orchestrator-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Review Orchestrator safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Review Orchestrator?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Review Orchestrator free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Review Orchestrator?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Review Orchestrator by tomevault-io

Name: Code Review Orchestrator
Author: tomevault-io

File contents

Activation Contract

Triggered on pre-commit hook or when user says "code review", "review all", "quality check", "audit code", "orchestrator", or similar.

Hard Rules

MUST run Security + Quality quick scan on every pre-commit
MUST run all 7 dimensions pre-merge
MUST block commit on CRITICAL findings (exit code 1)
MUST generate a report at docs/code-reviews/
MUST classify every finding by severity
MUST NOT modify source files during review
MUST keep quick scan under 30 seconds

Decision Gates

Gate	Options	Rule
Scope	all, security, quality, testing, docs, api, git, quick, full	quick = Security+Quality; full = all 7
Severity action	CRITICAL block, HIGH warn+review, MEDIUM info, LOW suggest	CRITICAL always blocks (exit 1)
Trigger	pre-commit auto vs manual	Auto runs quick scope only

Execution Steps

Detect trigger (pre-commit hook or manual request)
Resolve scope — quick (Security+Quality) or full (all 7)
Load config from configs/review-config.json
Execute scans for selected dimensions
Classify each finding by severity
Generate report (console + file at docs/code-reviews/)
Block if CRITICAL found (exit 1), otherwise allow (exit 0)

Output Contract

Return severity breakdown, categorized issues (file:line, description, recommendation), report file path, and exit code (1 if blocked).

References

references/seven-dimensions.md — Dimension descriptions and scope mapping
references/severity-matrix.md — Severity levels with actions
references/commands.md — Full command reference and performance
references/report-format.md — Console and file report templates
references/judgment-day.md — Dual review protocol
references/config-example.md — Review configuration JSON
references/integration.md — Git hooks and CI/CD setup

Source: EmmanuelOrtiz87/gentle-vanguard — distributed by TomeVault.

---name: code-review-orchestrator-2description: Triggered on pre-commit hook or when user says "code review", "review all", "quality check", "audit Use when this capability is needed.---## Activation ContractTriggered on pre-commit hook or when user says "code review", "review all", "quality check", "auditcode", "orchestrator", or similar.## Hard Rules- MUST run Security + Quality quick scan on every pre-commit- MUST run all 7 dimensions pre-merge- MUST block commit on CRITICAL findings (exit code 1)- MUST generate a report at docs/code-reviews/- MUST classify every finding by severity- MUST NOT modify source files during review- MUST keep quick scan under 30 seconds## Decision Gates| Gate | Options | Rule || --------------- | ------------------------------------------------------------ | -------------------------------------- || Scope | all, security, quality, testing, docs, api, git, quick, full | quick = Security+Quality; full = all 7 || Severity action | CRITICAL block, HIGH warn+review, MEDIUM info, LOW suggest | CRITICAL always blocks (exit 1) || Trigger | pre-commit auto vs manual | Auto runs quick scope only |## Execution Steps1. Detect trigger (pre-commit hook or manual request)2. Resolve scope — quick (Security+Quality) or full (all 7)3. Load config from configs/review-config.json4. Execute scans for selected dimensions5. Classify each finding by severity6. Generate report (console + file at docs/code-reviews/)7. Block if CRITICAL found (exit 1), otherwise allow (exit 0)## Output ContractReturn severity breakdown, categorized issues (file:line, description, recommendation), report filepath, and exit code (1 if blocked).## References- `references/seven-dimensions.md` — Dimension descriptions and scope mapping- `references/severity-matrix.md` — Severity levels with actions- `references/commands.md` — Full command reference and performance- `references/report-format.md` — Console and file report templates- `references/judgment-day.md` — Dual review protocol- `references/config-example.md` — Review configuration JSON- `references/integration.md` — Git hooks and CI/CD setup---> Source: [EmmanuelOrtiz87/gentle-vanguard](https://github.com/EmmanuelOrtiz87/gentle-vanguard) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions

Code Review Orchestrator