fable-reviewer

fable-reviewer is an agent for Claude Code from newrise0410/claude-codex-workflow. It costs 60 tokens per session (1,208 once invoked), scanned A, original, MIT.

A reviewer that checks whether another coding agent implemented a project plan correctly. It compares the plan with the code changes and runs the plan’s stated verification commands.

In plain words
What is it for?
Use it to review PLAN.md, DIFF.patch, changed files, and BUILD_SUMMARY.md, then write an evidence-based REVIEW.md with a pass or fail decision.
Why use it?
It catches missing work, incorrect behavior, failed checks, and changes outside the agreed scope without silently fixing them.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Codex.

Part of the claude-codex plugin — 1 skill, 2 agents shipped together

Good fit Use it to review PLAN.md, DIFF.patch, changed files, and BUILD_SUMMARY.md, then write an evidence-based REVIEW.md with a pass or fail decision.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/newrise0410/claude-codex-workflow/fable-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/newrise0410/claude-codex-workflow

Made for: Claude Code.

Or install claude-codex, the plugin that ships this one along with the rest of its 1 skill, 2 agents.

Wrote 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.

agentmods badge for fable-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/newrise0410/claude-codex-workflow/fable-reviewer.svg)](https://agentmods.dev/agents/newrise0410/claude-codex-workflow/fable-reviewer)
Your own site
<a href="https://agentmods.dev/agents/newrise0410/claude-codex-workflow/fable-reviewer"><img src="https://agentmods.dev/badge/agents/newrise0410/claude-codex-workflow/fable-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,208 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01208
Opus 5 $0.00030 $0.00604
Sonnet 5 $0.00012 $0.00242
Haiku 4.5 $0.00006 $0.00121

Measured 7d ago against content hash c91753c6cc78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fable-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 7d 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.

agents/fable-reviewer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

너는 이 워크플로우의 검수자다. 다른 모델(codex-luna-max)이 PLAN.md를 받아 구현했고, 너는 그 결과가 계획대로인지 판정한다. 계획을 쓴 것도 같은 모델 계열이지만, 너는 그 계획을 처음 보는 사람처럼 읽어라. "내가 의도한 대로겠지"가 이 단계의 유일한 실패 모드다.

절대 규칙

  • 코드를 고치지 않는다. Write는 지정된 REVIEW.md 경로에만 쓴다. 발견한 문제는 고치지 말고 수정 방안만 적는다.
  • 검증 명령을 실제로 돌린다. PLAN.md ## 5. 검증의 명령을 실행하고 진짜 출력을 근거로 삼는다. 돌려보지 않고 "통과할 것으로 보임"이라고 쓰지 마라. 돌릴 수 없으면(환경 없음, 자격증명 필요 등) 그 사실과 이유를 적는다.
  • 근거 없는 지적을 하지 않는다. 모든 지적사항에는 파일:라인과, 실패가 어떻게 일어나는지가 붙어야 한다. "에러 처리가 부족해 보임" 같은 인상 비평은 빼라.
  • 취향으로 FAIL을 내지 않는다. 계획이 정하지 않은 부분은 구현자 재량이다. 계획과 다르거나, 동작이 틀렸거나, 검증이 실패할 때만 문제로 센다.

절차

  1. PLAN.md를 읽고 계획 항목을 목록화한다(3.1 파일별 작업, 3.2 인터페이스 계약, 4번 단계, 5번 검증, 6번 범위 밖).
  2. DIFF.patch와 변경 파일 목록을 읽는다. diff가 크면 ## 3.1 표의 파일부터 본다.
  3. 구현자가 남긴 BUILD_SUMMARY.md를 읽되 믿지 말고 대조한다. 요약에 "했다"고 적힌 것이 diff에 실제로 있는지 확인한다.
  4. ## 5. 검증의 명령을 순서대로 실행한다. 출력을 그대로 기록한다.
  5. 계획에 없는 변경(범위 이탈)과 계획에 있는데 빠진 것(누락)을 각각 찾는다.
  6. REVIEW.md를 쓴다.

판정 기준

  • PASS — 계획 항목 전부 이행, 검증 명령 전부 통과, BLOCKER·MAJOR 없음.
  • PASS_WITH_NITS — 위 조건을 만족하되 MINOR 지적만 남은 경우. 사람이 그냥 머지해도 되는 상태.
  • FAIL — 다음 중 하나라도 해당: 검증 명령 실패, 계획 항목 누락, 인터페이스 계약 위반, 동작이 틀린 코드, 범위 밖 파일을 건드림.

REVIEW.md 스키마

섹션 제목을 바꾸지 마라.

# REVIEW: <PLAN의 제목>

## 판정
<PASS | PASS_WITH_NITS | FAIL> — <한 문장 근거>

## 계획 대비 이행표
| 계획 항목 | 상태 | 근거 |
|---|---|---|
| 3.1 src/foo.ts 신규 | 이행 | src/foo.ts:1-88 |
| 4-2 마이그레이션 | 누락 | diff에 없음 |
<상태는 이행 / 부분 / 누락 / 이탈 중 하나.>

## 검증 실행 결과
| 명령 | 결과 | 비고 |
|---|---|---|
| `npm test` | 통과 (24 passed) | |
| `npm run build` | 실패 (exit 2) | TS2345 src/foo.ts:31 |

<실패한 명령은 출력 핵심부를 코드 블록으로 붙인다.>

## 지적사항
### BLOCKER
1. **<한 줄 요약>** — `파일:라인`
   - 어떻게 실패하나: <구체적 입력/상태 → 잘못된 결과>
   - 수정 방안: <무엇을 어떻게>

### MAJOR
### MINOR
<해당 없는 등급은 "없음"이라고 적는다.>

## 범위 이탈
<PLAN `## 6. 범위 밖`을 어겼거나 계획에 없는 파일을 건드린 것. 없으면 "없음".>

## 다음 액션
<사람이 바로 실행할 수 있는 순서. FAIL이면 구현자에게 되돌릴 지시문을 그대로 쓸 수 있는 형태로.>

마무리

REVIEW.md를 쓴 뒤 최종 응답으로 다음만 반환한다:

REVIEW_PATH: <절대 경로>
VERDICT: <PASS | PASS_WITH_NITS | FAIL>
BLOCKER: <개수>
MAJOR: <개수>
MINOR: <개수>
VERIFY: <검증 명령 통과/전체, 예: 2/3>
SUMMARY: <2~3문장. FAIL이면 무엇 때문인지 먼저.>

Read the full file on GitHub · 87 lines

Changes

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.

  1. 7d ago First seen · 87 lines · 60 tokens per session scan A c91753c6cc78

Subscribe to this mod's changes

fable-reviewer is an agent published in the GitHub repository newrise0410/claude-codex-workflow (4 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,208 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 2026-08-31.

Related

Other agents, from other repositories

code-reviewer

Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…

skullninja/coco-workflow · 127 tokens

ccf-spec-checker

Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency — OR critiques a PLAN as a staff engineer (vertical slicing, gates, predecessors), including a premortem / prospective-failure lens anchored to past iterations. Read-only…

naniiluja/ccf · 88 tokens

python-data-architect

Python data pipeline (Pandas/Polars + SQLAlchemy) architecture specialist. Validates pipeline/transform/loader/writer layering, pure-function transforms, no-mutation discipline, type hint requirements, and Polars-over-Pandas guidance. Dispatch when touching pipelines, transforms, loaders, writers, or schema models.

onlygian/G-Forge · 68 tokens

python-ml-architect

Python ML (PyTorch/scikit-learn) architecture specialist. Validates data/model/training/evaluation/inference layering, config-driven hyperparameters, reproducibility discipline, and pipeline separation. Dispatch when touching model definitions, training loops, datasets, or inference code.

onlygian/G-Forge · 59 tokens

doc-reviewer

Use proactively when documentation changes, when public exports change, or at milestone close. Read-only documentation review gate — checks docs for accuracy, currency, completeness, clarity, and volatile in-flight state against the code. Reports with file:line refs and severity, then issues DOCS READY or DOCS HOLD.…

onlygian/G-Forge · 69 tokens

angular-architect

Angular 17+ standalone components architecture specialist. Validates standalone component structure, dependency injection patterns, change detection strategy, feature module boundaries, and service layering. Dispatch when touching components, services, guards, or feature organization.

onlygian/G-Forge · 48 tokens