Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Dannykkh/skill-olympus --skill code-reviewergit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/dannykkh/skill-olympus/code-reviewer)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/code-reviewer"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/code-reviewer/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/dannykkh/skill-olympus/code-reviewer"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 325 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Tool Misuse · line 292 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00187 | $0.05703 |
| Opus 5.5 | $0.00075 | $0.02281 |
| Sonnet 5.5 | $0.00037 | $0.01141 |
| Haiku 4.5 | $0.00019 | $0.00570 |
Grade A, and why
code-reviewer scanned grade A with 2 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- async def 안 동기 subprocess.run, open, requests.get → asyncio.to_thread 사용 Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- async def 안 동기 subprocess.run, open, requests.get → asyncio.to_thread 사용 How it starts
The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer v4 — Policy Layer + Native Engine
PR 단위 코드 리뷰 오케스트레이터. v4부터 리뷰 엔진과 정책 레이어를 분리합니다.
리뷰 요청
│
├─ Security audit 요청 → references/security-audit.md
├─ Step 0~1: 베이스 브랜치 + 리뷰 대상 확인
├─ Step 2: 엔진 선택 (CLI 감지)
│ ├─ 경로 A: Claude/Grok → 사용 가능한 review 엔진
│ ├─ 경로 B: Codex → 네이티브 codex review
│ └─ 경로 C: 풀 경로 (네이티브 없음 — Antigravity 등)
└─ Step 3: 정책 레이어 P1~P5 (공통)
P1 Scope Drift → P2 도메인 보강 패스 → P3 Suppressions
→ P4 Action Triage → P5 통합 보고서
설계 원칙: 네이티브 엔진이 잘하는 일반 리뷰(버그, 보안 기본기, 성능)는 중복 구현하지 않는다. 이 스킬은 네이티브가 안 하는 것만 담당한다.
적용 시점
- 명시적 리뷰 요청 시 ("코드 리뷰 해줘", "review")
- 명시적 보안 감사 요청 시 ("보안 감사", "security review", "취약점 분석")
- PR 생성 전 (
/ship전) - 코드 작성 완료 시 자동 제안
보안 감사 요청이면 Step 0~3 대신 Repository Security Audit Contract를 읽어 범위를 정합니다. 일반 코드 리뷰와 달리 전체 저장소 감사를 자동 제안하거나 암묵적으로 실행하지 않습니다.
API·입력 처리 변경의 필수 검토 (모든 리뷰 경로)
API·인증/권한·입력 스키마·데이터 바인딩·업무 상태·공통 검증기 변경이면
API 직접 호출·서버 검증 계약을
변경 범위에 적용합니다. 경로 A/B/C, 소규모 diff, specialist 생략 여부와 무관합니다.
파일명 감지만으로 제외하지 말고 실제 호출 경로를 확인합니다. 네이티브 리뷰 결과의 누락을 이 계약으로
보강하고 중복 발견은 합칩니다. 위임 프롬프트에도 해당 계약을 전달하며 메인이 커버리지를 확인합니다.
실제 실행 근거가 없는 부분은 UNVERIFIED/NOT RUN으로 보고합니다.
Step 0: 베이스 브랜치 감지
# 플랫폼 감지
_REMOTE_URL=$(git remote get-url origin 2>/dev/null || echo "unknown")
# 베이스 브랜치 결정
_BASE=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||')
[ -z "$_BASE" ] && git rev-parse --verify origin/main &>/dev/null && _BASE="main"
[ -z "$_BASE" ] && git rev-parse --verify origin/master &>/dev/null && _BASE="master"
[ -z "$_BASE" ] && _BASE="main"
echo "BASE: $_BASE"
echo "BRANCH: $(git branch --show-current 2>/dev/null)"
Step 1: 리뷰 대상 확인
git status --short로 staged, unstaged, untracked 변경을 먼저 확인합니다.- 작업 트리에 변경이 있으면 현재 브랜치가 base여도
--uncommitted범위로 검토합니다. - 작업 트리가 깨끗하면 기존
origin/$_BASEref와git diff origin/$_BASE...HEAD --stat을 사용합니다. - ref가 없거나 사용자가 최신 원격 기준을 요청한 경우에만
git fetch origin $_BASE --quiet를 실행합니다. - 두 범위 모두 diff가 없을 때만 **"리뷰할 변경이 없습니다."**로 중단합니다.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- checklists/suppressions.md 2.6 KB
- references/review-examples.md 4.6 KB
- references/security-audit.md 9.6 KB
- specialists/api-contract.md 2.1 KB
- specialists/data-migration.md 2.1 KB
- specialists/design.md 2.8 KB
- specialists/maintainability.md 5.0 KB
- specialists/performance.md 2.2 KB
- specialists/security.md 2.8 KB
- specialists/testing.md 1.9 KB
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.
- 1mo ago Changed · +9 lines 1db8dcfe8a5e
- 1mo ago Changed 6bec5b63c69a
- 1mo ago First seen · 478 lines · 187 tokens per session scan A fdd8187a1ca1
code-reviewer is a skill published in the GitHub repository Dannykkh/skill-olympus (7 stars, last pushed yesterday), licensed MIT. It adds 187 tokens to every session and 5,703 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
audit-project
Audits the Claude Code configuration of a project against the dotforge template. Generates a report with score and gaps.
project-audit
Repository audit for non-website projects (CLI, libs, backend, monorepo). Use when: "project-audit", "project audit", "repo audit", "code audit".
adversarial-review
Critical review (min. 5 findings). Modes: code, audit, plan. Use when: "review", "critical review", "code review", "plan review", "audit review".
inline-review
Quick self-review checklist after code changes. Lightweight alternative to adversarial-review. Use when: "review my changes", "self-review", "quick review", "check my work", or automatically after significant edits.
review-team
Launch parallel code review agents for comprehensive multi-perspective review. Use when: "review team", "full review", "multi-review", "review-team".
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…