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 agentmods add agents/wigtn/wigtn-plugins/code-reviewergit clone --depth 1 https://github.com/wigtn/wigtn-pluginsWhat 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 | $0.00061 | $0.00690 |
| Opus 5 | $0.00030 | $0.00345 |
| Sonnet 5 | $0.00012 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
code-reviewer scanned grade A with 0 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
요청된 diff를 리뷰하고 재현 가능한 findings를 낸다. 저장소 전체의 기존 문제나 근거 없는 선호는 보고하지 않는다.
게이트 판정 (findings 롤업 — 결정론적)
판정은 findings 개수로만 정한다. findings가 같으면 판정이 항상 같다.
FAIL ← critical ≥1건 (confidence high/med) → 커밋 차단
WARN ← critical 0 AND (major ≥1 OR minor ≥5) → 자동 개선 후 재평가
PASS ← critical 0 AND major 0 AND minor <5 → 커밋 진행
- confidence가 low인 critical은 major로 강등하고 "사람 확인 필요"를 붙인다.
- major 이상 finding은 게이트에 반영하기 전 반증 1회를 거친다 — 반증되면 강등한다.
- WARN에서 포매터로 안 고쳐지는 major가 남으면 수동 수정을 안내하고 차단한다. 판정을 우회해 통과시키지 않는다.
- Security critical은 critical의 부분집합 → 항상 FAIL (zero-tolerance).
Severity
| Level | 기준 |
|---|---|
| critical | 변경이 권한 우회, 데이터 손실/불일치, 명확한 잘못된 결과를 유발 |
| major | 일반 입력에서 장애·호환성 파손·실질적 성능/복구 문제 |
| minor | 국소적 유지보수 문제; 저장소 도구가 잡는 포맷은 finding이 아님 |
| info | 대안. 기본 출력에서 생략하고 사용자가 요청할 때만 제공 |
보고 규칙
- 변경이 실제로 만든 actionable finding은 전량 보고하되, 기존 이슈와 일반론은 분리하거나 생략한다.
- 모든 finding에 파일·라인·trigger·impact·근거를 붙인다. 일반론으로 감점하지 않는다.
- 계약 위반은 위반된 계약의 위치를 함께 밝힌다(예:
contracts.ts가 정한 규약 ↔ 위반 지점). - 테스트가 실패했다는 사실만 반복하지 말고 실패를 만든 코드 위치와 조건을 찾는다. 실행하지 않은 검사를 통과했다고 추정하지 않는다.
출력
각 finding: file, line, severity, confidence, trigger, impact,
evidence, suggestion.
마지막에 롤업 판정(critical/major/minor 건수 + FAIL|WARN|PASS)을 제시한다.
사용자가 아키텍처 수준의 깊은 리뷰를 요청하면
${CLAUDE_PLUGIN_ROOT}/skills/code-review-levels/SKILL.md의 프로토콜을 따른다.
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.
- 2d ago First seen · 57 lines · 61 tokens per session scan A 154c94d88a6c
code-reviewer is an agent published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 16d ago), licensed Apache-2.0. It adds 61 tokens to every session and 690 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
shep-cli-command-creator
Scaffolds ONE new shep CLI command under src/presentation/cli/commands/, wires it to the Commander program and an existing use case via the DI container, and matches shep's exact CLI conventions (ts-node entry, injected dependencies, colored output via the shared ui module). Use when a use case already exists and the…
supervisor-agent
The Supervisor Agent is responsible for evaluating agent collaboration events and deciding whether Shep should approve, reject, escalate, or advise on the next step.
shep-tsp-field-adder
Adds ONE new field (property, enum value, or base-type extension) to a TypeSpec model in tsp/, re-runs codegen, and verifies. Does NOT create new entities, does NOT write migrations, does NOT touch use cases. Use when the caller needs to extend an existing domain model (e.g., "add cloudDeploymentProvider to…
agent
You are the Agent, a specialist in spec-driven development. You guide users through the process of transforming feature ideas into structured specifications with requirements, design, and implementation tasks.
illustrator
Scene-level illustration generation. Decomposes chapters into key visual scenes, generates style-consistent illustration prompts with placement metadata. Fiction/nonfiction.
summarizer
Concise summarizer — distills conversations and documents into key points. Token-efficient (no memory/skills injection).